refactor: delete redundant _prepare_project_layout wrapper

resolve_project_layout() from domain already handles mkdir.
Callers now use the domain function directly.

Tests: 1253 passed

.gitattributes

@@ -0,0 +1,15 @@
+*.py text eol=lf
+*.md text eol=lf
+*.yml text eol=lf
+*.yaml text eol=lf
+*.toml text eol=lf
+*.json text eol=lf
+*.txt text eol=lf
+*.html text eol=lf
+*.css text eol=lf
+*.js text eol=lf
+*.sh text eol=lf
+*.cfg text eol=lf
+*.ini text eol=lf
+*.svg text eol=lf
+*.j2 text eol=lf

.github/FUNDING.yml

@@ -0,0 +1,15 @@
+# These are supported funding model platforms
+
+github: [jborza, jeremiahsb, mohangk]
+patreon: # Replace with a single Patreon username
+open_collective: # Replace with a single Open Collective username
+ko_fi: # Replace with a single Ko-fi username
+tidelift: # Replace with a single Tidelift platform-name/package-name e.g., npm/babel
+community_bridge: # Replace with a single Community Bridge project-name e.g., cloud-foundry
+liberapay: # Replace with a single Liberapay username
+issuehunt: # Replace with a single IssueHunt username
+lfx_crowdfunding: # Replace with a single LFX Crowdfunding project-name e.g., cloud-foundry
+polar: # Replace with a single Polar username
+buy_me_a_coffee: # Replace with a single Buy Me a Coffee username
+thanks_dev: # Replace with a single thanks.dev username
+custom: # Replace with up to 4 custom sponsorship URLs e.g., ['link1', 'link2']

.github/workflows/test_pip.yml

@@ -1,7 +1,9 @@
-name: pip install
+name: CI
-run-name: pip install
+run-name: CI
+
 on:
   push:
+    branches: [main]
     paths:
       - '**.py'
       - 'pyproject.toml'
@@ -11,23 +13,41 @@ on:
       - 'pyproject.toml'
       - '.github/workflows/**'
   workflow_dispatch:
+
 jobs:
-  install-and-run:
+  test:
     strategy:
       matrix:
-        os: [ubuntu-latest, macos-latest, windows-latest]
+        os: [ubuntu-latest, macos-14, windows-latest]
         python-version: ['3.12']
       fail-fast: false
-    continue-on-error: true
     runs-on: ${{ matrix.os }}
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v4
+        uses: actions/checkout@v7
+
       - name: Set up Python
-        uses: actions/setup-python@v5
+        uses: actions/setup-python@v6
         with:
           python-version: ${{ matrix.python-version }}
-      - name: Install from repository
+
-        run: python -m pip install .
+      - name: Install uv
-      #- name: Run abogen
+        uses: astral-sh/setup-uv@v8.3.1
-      #  run: abogen
+        with:
+          enable-cache: true
+          prune-cache: false
+          cache-dependency-glob: pyproject.toml
+
+      - name: Install system dependencies (Ubuntu)
+        if: runner.os == 'Linux'
+        run: sudo apt-get update && sudo apt-get install -y libegl1
+
+      - name: Install dependencies
+        run: uv pip install --system .[dev]
+        env:
+          UV_LINK_MODE: copy
+
+      - name: Run tests
+        env:
+          QT_QPA_PLATFORM: offscreen
+        run: pytest tests/ -v --tb=short

.github/workflows/test_publish.yml

@@ -18,7 +18,7 @@ jobs:
   build:
     runs-on: ubuntu-latest
     steps:
-    - uses: actions/checkout@v4
+    - uses: actions/checkout@v7
 
     - name: Login to Github Container Registry
       # Only if we need to push an image

.gitignore

@@ -38,3 +38,4 @@ dist/
 .old/
 test_assets/
 dev_notes/
+.claude/

abogen/VERSION

@@ -1 +1 @@
-1.3.0
+1.3.1

abogen/book_parser.py

@@ -915,7 +915,11 @@ class EpubParser(BaseBookParser):
 
             if slice_html.strip():
                 slice_soup = BeautifulSoup(slice_html, "html.parser")
-                for tag in slice_soup.find_all(["p", "div"]):
+
+                # Add line breaks after block-level elements to ensure pauses in speech
+                for tag in slice_soup.find_all(
+                    ["p", "div", "h1", "h2", "h3", "h4", "h5", "h6", "li", "blockquote"]
+                ):
                     tag.append("\n\n")
 
                 for ol in slice_soup.find_all("ol"):

abogen/constants.py

@@ -63,64 +63,6 @@ SUPPORTED_INPUT_FORMATS = [
 # 384 if self.lang_code in 'ab':
 SUPPORTED_LANGUAGES_FOR_SUBTITLE_GENERATION = list(LANGUAGE_DESCRIPTIONS.keys())
 
-# Voice and sample text constants
-VOICES_INTERNAL = [
-    "af_alloy",
-    "af_aoede",
-    "af_bella",
-    "af_heart",
-    "af_jessica",
-    "af_kore",
-    "af_nicole",
-    "af_nova",
-    "af_river",
-    "af_sarah",
-    "af_sky",
-    "am_adam",
-    "am_echo",
-    "am_eric",
-    "am_fenrir",
-    "am_liam",
-    "am_michael",
-    "am_onyx",
-    "am_puck",
-    "am_santa",
-    "bf_alice",
-    "bf_emma",
-    "bf_isabella",
-    "bf_lily",
-    "bm_daniel",
-    "bm_fable",
-    "bm_george",
-    "bm_lewis",
-    "ef_dora",
-    "em_alex",
-    "em_santa",
-    "ff_siwis",
-    "hf_alpha",
-    "hf_beta",
-    "hm_omega",
-    "hm_psi",
-    "if_sara",
-    "im_nicola",
-    "jf_alpha",
-    "jf_gongitsune",
-    "jf_nezumi",
-    "jf_tebukuro",
-    "jm_kumo",
-    "pf_dora",
-    "pm_alex",
-    "pm_santa",
-    "zf_xiaobei",
-    "zf_xiaoni",
-    "zf_xiaoxiao",
-    "zf_xiaoyi",
-    "zm_yunjian",
-    "zm_yunxi",
-    "zm_yunxia",
-    "zm_yunyang",
-]
-
 # Voice and sample text mapping
 SAMPLE_VOICE_TEXTS = {
     "a": "This is a sample of the selected voice.",

abogen/conversion.py

@@ -1,16 +0,0 @@
-"""Backwards-compatible re-export of conversion module.
-
-The PyQt-based implementation lives in abogen.pyqt.conversion.
-The web-based implementation is in abogen.webui.conversion_runner.
-"""
-
-from __future__ import annotations
-
-# Re-export PyQt conversion classes for backwards compatibility
-from abogen.pyqt.conversion import (  # noqa: F401
-    ConversionThread,
-    VoicePreviewThread,
-    PlayAudioThread,
-)
-
-__all__ = ["ConversionThread", "VoicePreviewThread", "PlayAudioThread"]

abogen/domain/audio_buffer.py

@@ -0,0 +1,239 @@
+"""Audio buffer operations for audiobook generation.
+
+This module provides core audio buffer manipulation functions including:
+- Silence generation
+- Audio mixing
+- Audio normalization
+- Audio buffer resizing
+"""
+
+from __future__ import annotations
+
+from typing import Optional
+
+import numpy as np
+
+# Standard sample rate used throughout the application
+SAMPLE_RATE = 24000
+
+
+def create_silence(duration_seconds: float) -> np.ndarray:
+    """Create a silence audio buffer.
+    
+    Args:
+        duration_seconds: Duration of silence in seconds.
+        
+    Returns:
+        Numpy array of float32 zeros with length = duration_seconds * SAMPLE_RATE.
+        Returns empty array if duration is <= 0.
+    """
+    if duration_seconds <= 0:
+        return np.array([], dtype="float32")
+    
+    samples = int(round(duration_seconds * SAMPLE_RATE))
+    if samples <= 0:
+        return np.array([], dtype="float32")
+    
+    return np.zeros(samples, dtype="float32")
+
+
+def mix_audio(
+    target: np.ndarray,
+    source: np.ndarray,
+    start_sample: int,
+    end_sample: Optional[int] = None,
+) -> np.ndarray:
+    """Mix source audio into target buffer at specified position.
+    
+    This performs additive mixing (target += source). The target buffer
+    is extended if necessary to accommodate the source audio.
+    
+    Args:
+        target: The target audio buffer to mix into.
+        source: The source audio buffer to mix.
+        start_sample: Starting sample index in target buffer.
+        end_sample: Optional end sample index. If None, calculated from source length.
+        
+    Returns:
+        The target buffer (possibly extended). If target was extended, returns new array.
+    """
+    if source.size == 0:
+        return target
+    
+    if end_sample is None:
+        end_sample = start_sample + len(source)
+    
+    # Extend target buffer if needed
+    if end_sample > len(target):
+        new_length = end_sample
+        new_target = np.concatenate([
+            target,
+            np.zeros(new_length - len(target), dtype="float32")
+        ])
+        target = new_target
+    
+    # Perform the mix (additive)
+    target[start_sample:end_sample] += source
+    return target
+
+
+def normalize_audio(
+    audio: np.ndarray,
+    target_peak: float = 1.0,
+) -> np.ndarray:
+    """Normalize audio buffer to prevent clipping.
+    
+    If the audio exceeds the target peak (default 1.0), it is scaled down
+    proportionally to prevent distortion.
+    
+    Args:
+        audio: Input audio buffer.
+        target_peak: Target maximum amplitude (default 1.0).
+        
+    Returns:
+        Normalized audio buffer (new array, original is not modified).
+    """
+    if audio.size == 0:
+        return audio.copy()
+    
+    max_amplitude = float(np.abs(audio).max())
+    
+    if max_amplitude <= target_peak:
+        return audio.copy()
+    
+    # Scale down to prevent clipping
+    scale_factor = target_peak / max_amplitude
+    return (audio * scale_factor).astype("float32")
+
+
+def ensure_buffer_size(
+    buffer: np.ndarray,
+    min_samples: int,
+) -> np.ndarray:
+    """Ensure audio buffer is at least min_samples long.
+    
+    If buffer is shorter, it is extended with zeros.
+    
+    Args:
+        buffer: Input audio buffer.
+        min_samples: Minimum required length in samples.
+        
+    Returns:
+        Buffer of at least min_samples length (new array if extended).
+    """
+    if len(buffer) >= min_samples:
+        return buffer
+    
+    new_buffer = np.zeros(min_samples, dtype="float32")
+    new_buffer[:len(buffer)] = buffer
+    return new_buffer
+
+
+def concatenate_audio(*buffers: np.ndarray) -> np.ndarray:
+    """Concatenate multiple audio buffers.
+    
+    Args:
+        *buffers: Audio buffers to concatenate.
+        
+    Returns:
+        Single concatenated audio buffer.
+    """
+    non_empty = [b for b in buffers if b.size > 0]
+    if not non_empty:
+        return np.array([], dtype="float32")
+    return np.concatenate(non_empty)
+
+
+def audio_duration(audio: np.ndarray, sample_rate: int = SAMPLE_RATE) -> float:
+    """Calculate duration of audio buffer in seconds.
+    
+    Args:
+        audio: Audio buffer.
+        sample_rate: Sample rate in Hz (default SAMPLE_RATE).
+        
+    Returns:
+        Duration in seconds.
+    """
+    return len(audio) / sample_rate
+
+
+def samples_for_duration(duration_seconds: float, sample_rate: int = SAMPLE_RATE) -> int:
+    """Calculate number of samples for a given duration.
+    
+    Args:
+        duration_seconds: Duration in seconds.
+        sample_rate: Sample rate in Hz (default SAMPLE_RATE).
+        
+    Returns:
+        Number of samples (rounded to nearest integer), or 0 if duration is <= 0.
+    """
+    if duration_seconds <= 0:
+        return 0
+    return int(round(duration_seconds * sample_rate))
+
+
+def fit_audio_to_duration(
+    audio: np.ndarray,
+    target_duration: float,
+    sample_rate: int = SAMPLE_RATE,
+) -> np.ndarray:
+    """Pad or trim audio to match target duration.
+
+    Args:
+        audio: Input audio buffer.
+        target_duration: Desired duration in seconds.
+        sample_rate: Sample rate in Hz.
+
+    Returns:
+        Audio buffer of exact length target_duration * sample_rate.
+    """
+    target_samples = int(target_duration * sample_rate)
+    if len(audio) < target_samples:
+        padding = np.zeros(target_samples - len(audio), dtype="float32")
+        return np.concatenate([audio, padding])
+    return audio[:target_samples]
+
+
+def ffmpeg_time_stretch(
+    audio: np.ndarray,
+    speed_factor: float,
+    sample_rate: int = SAMPLE_RATE,
+) -> np.ndarray:
+    """Time-stretch audio using FFmpeg's atempo filter.
+
+    Args:
+        audio: Input audio buffer (float32).
+        speed_factor: Speed multiplier (>1.0 = faster).
+        sample_rate: Sample rate in Hz.
+
+    Returns:
+        Time-stretched audio buffer.
+    """
+    import math
+    import subprocess
+
+    import static_ffmpeg
+
+    if speed_factor <= 1.0 or audio.size == 0:
+        return audio
+
+    static_ffmpeg.add_paths()
+    num_stages = max(1, int(math.ceil(math.log(speed_factor) / math.log(2.0))))
+    tempo = speed_factor ** (1.0 / num_stages)
+    filter_str = ",".join([f"atempo={tempo:.6f}"] * num_stages)
+
+    proc = subprocess.Popen(
+        [
+            "ffmpeg", "-y",
+            "-f", "f32le", "-ar", str(sample_rate), "-ac", "1",
+            "-i", "pipe:0",
+            "-filter:a", filter_str,
+            "-f", "f32le", "-ar", str(sample_rate), "-ac", "1",
+            "pipe:1",
+        ],
+        stdin=subprocess.PIPE,
+        stdout=subprocess.PIPE,
+        stderr=subprocess.PIPE,
+    )
+    out, _ = proc.communicate(input=audio.tobytes())
+    return np.frombuffer(out, dtype="float32")

abogen/domain/audio_helpers.py

@@ -0,0 +1,118 @@
+"""Audio helper utilities.
+
+Functions for building ffmpeg commands, converting audio formats,
+and applying chapter metadata to MP4 files.
+"""
+
+from __future__ import annotations
+
+from pathlib import Path
+from typing import Any, Dict, List, Optional
+
+import numpy as np
+
+
+SAMPLE_RATE = 24000
+
+
+def build_ffmpeg_command(path: Path, fmt: str, metadata: Optional[Dict[str, str]] = None) -> list[str]:
+    from abogen.infrastructure.exporters import ExportService
+
+    base = [
+        "ffmpeg",
+        "-y",
+        "-f",
+        "f32le",
+        "-ar",
+        str(SAMPLE_RATE),
+        "-ac",
+        "1",
+        "-i",
+        "pipe:0",
+    ]
+    if fmt == "mp3":
+        base += ["-c:a", "libmp3lame", "-qscale:a", "2"]
+    elif fmt == "opus":
+        base += ["-c:a", "libopus", "-b:a", "24000"]
+    elif fmt == "m4b":
+        base += ["-c:a", "aac", "-q:a", "2", "-movflags", "+faststart+use_metadata_tags"]
+    else:
+        base += ["-c:a", "copy"]
+
+    if metadata:
+        svc = ExportService()
+        base.extend(svc._metadata_to_ffmpeg_args(metadata))
+    base.append(str(path))
+    return base
+
+
+def to_float32(audio_segment) -> np.ndarray:
+    if audio_segment is None:
+        return np.zeros(0, dtype="float32")
+
+    tensor = audio_segment
+    if hasattr(tensor, "detach"):
+        tensor = tensor.detach()
+    if hasattr(tensor, "cpu"):
+        try:
+            tensor = tensor.cpu()
+        except Exception:
+            pass
+    if hasattr(tensor, "numpy"):
+        return np.asarray(tensor.numpy(), dtype="float32").reshape(-1)
+    return np.asarray(tensor, dtype="float32").reshape(-1)
+
+
+def apply_m4b_chapters_with_mutagen(
+    audio_path: Path,
+    chapters: List[Dict[str, Any]],
+) -> bool:
+    """Apply chapter atoms to an MP4/M4B file using mutagen.
+
+    Returns True if chapters were written, False otherwise.
+    Raises ImportError if mutagen is not installed.
+    """
+    if not chapters:
+        return False
+
+    from fractions import Fraction
+    from mutagen.mp4 import MP4, MP4Chapter  # type: ignore[import]
+
+    mp4 = MP4(str(audio_path))
+
+    chapter_objects: List[MP4Chapter] = []
+    for index, entry in enumerate(sorted(chapters, key=lambda item: float(item.get("start") or 0.0))):
+        start_raw = entry.get("start")
+        if start_raw is None:
+            continue
+        try:
+            start_seconds = max(0.0, float(start_raw))
+        except (TypeError, ValueError):
+            continue
+
+        title_value = entry.get("title")
+        title_text = str(title_value) if title_value else f"Chapter {index + 1}"
+
+        start_fraction = Fraction(int(round(start_seconds * 1000)), 1000)
+        chapter_atom = MP4Chapter(start_fraction, title_text)
+
+        end_raw = entry.get("end")
+        if end_raw is not None:
+            try:
+                end_seconds = float(end_raw)
+            except (TypeError, ValueError):
+                end_seconds = None
+            if end_seconds is not None and end_seconds > start_seconds:
+                chapter_atom.end = Fraction(int(round(end_seconds * 1000)), 1000)
+
+        chapter_objects.append(chapter_atom)
+
+    if not chapter_objects:
+        return False
+
+    from typing import cast
+
+    mp4.chapters = cast(Any, chapter_objects)
+    mp4.save()
+
+    return True

abogen/domain/audio_sink.py

@@ -0,0 +1,131 @@
+"""Audio sink abstraction for unified audio output.
+
+Provides a context-manager-based abstraction for writing audio data
+to various output formats (WAV, FLAC via soundfile; compressed via ffmpeg).
+
+Usage:
+    with open_audio_sink(path, "wav") as sink:
+        sink.write(audio_data)
+"""
+
+from __future__ import annotations
+
+import os
+import subprocess
+import sys
+from dataclasses import dataclass
+from pathlib import Path
+from typing import Callable, Optional
+
+import numpy as np
+
+from abogen.domain.audio_buffer import SAMPLE_RATE
+from abogen.domain.audio_helpers import build_ffmpeg_command
+
+
+@dataclass(frozen=True)
+class AudioSink:
+    """Represents an open audio output target."""
+
+    write: Callable[[np.ndarray], None]
+    close: Callable[[], None]
+
+    def __enter__(self) -> AudioSink:
+        return self
+
+    def __exit__(self, exc_type, exc_val, exc_tb) -> None:
+        self.close()
+
+
+def _ensure_ffmpeg() -> None:
+    """Ensure static ffmpeg binaries are on PATH."""
+    import static_ffmpeg  # type: ignore
+
+    ffmpeg_cache_root = _get_ffmpeg_cache_root()
+    platform_cache = os.path.join(ffmpeg_cache_root, sys.platform)
+    os.makedirs(platform_cache, exist_ok=True)
+    try:
+        import static_ffmpeg.run as static_ffmpeg_run  # type: ignore
+
+        static_ffmpeg_run.LOCK_FILE = os.path.join(ffmpeg_cache_root, "lock.file")
+    except Exception:
+        pass
+    static_ffmpeg.add_paths(weak=True, download_dir=platform_cache)
+
+
+def _get_ffmpeg_cache_root() -> str:
+    from abogen.infrastructure.cache import get_internal_cache_path
+
+    return get_internal_cache_path("ffmpeg")
+
+
+def open_audio_sink(
+    path: Path,
+    fmt: str,
+    *,
+    metadata: Optional[dict[str, str]] = None,
+    cancel_check: Optional[Callable[[], bool]] = None,
+    extra_ffmpeg_args: Optional[list[str]] = None,
+    ffmpeg_cmd: Optional[list[str]] = None,
+) -> AudioSink:
+    """Open an audio output sink for writing raw float32 PCM samples.
+
+    Args:
+        path: Output file path.
+        fmt: Output format ("wav", "flac", "mp3", "opus", "m4b").
+        metadata: Optional metadata dict (ignored when ffmpeg_cmd is provided).
+        cancel_check: Optional callable; if it returns True, writes are silently skipped.
+        extra_ffmpeg_args: Optional extra args inserted after ffmpeg header (ignored when ffmpeg_cmd is provided).
+        ffmpeg_cmd: Optional pre-built ffmpeg command list (for m4b with cover art etc.).
+
+    Returns:
+        AudioSink with write() and close() methods.
+    """
+    fmt = fmt.lower()
+
+    if fmt in {"wav", "flac"}:
+        import soundfile as sf
+
+        soundfile_obj = sf.SoundFile(
+            path,
+            mode="w",
+            samplerate=SAMPLE_RATE,
+            channels=1,
+            format=fmt.upper(),
+        )
+
+        def _write_wav(data: np.ndarray) -> None:
+            if cancel_check and cancel_check():
+                return
+            soundfile_obj.write(data)
+
+        def _close_wav() -> None:
+            soundfile_obj.close()
+
+        return AudioSink(write=_write_wav, close=_close_wav)
+
+    # Compressed formats: pipe through ffmpeg
+    _ensure_ffmpeg()
+
+    if ffmpeg_cmd is not None:
+        cmd = list(ffmpeg_cmd)
+    else:
+        cmd = build_ffmpeg_command(path, fmt, metadata=metadata)
+        if extra_ffmpeg_args:
+            cmd[2:2] = extra_ffmpeg_args
+
+    process = subprocess.Popen(
+        cmd, stdin=subprocess.PIPE, stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL
+    )
+
+    def _write_compressed(data: np.ndarray) -> None:
+        if (cancel_check and cancel_check()) or process.stdin is None or process.stdin.closed:
+            return
+        process.stdin.write(data.tobytes())
+
+    def _close_compressed() -> None:
+        if process.stdin and not process.stdin.closed:
+            process.stdin.close()
+        process.wait()
+
+    return AudioSink(write=_write_compressed, close=_close_compressed)

abogen/domain/chapter_classification.py

@@ -0,0 +1,131 @@
+"""Heuristics for classifying chapters as content vs. supplements.
+
+A 'supplement' is any non-story material that a listener would typically
+skip: title page, copyright, table of contents, acknowledgements, etc.
+The scoring functions return a float; higher ⇒ more likely to be a
+supplement.  ``should_preselect_chapter`` turns that score into a
+boolean suitable for a web form default.
+"""
+
+from __future__ import annotations
+
+import re
+from typing import Any, Dict, List, Tuple
+
+# Compiled once at module load – these are immutable.
+
+_SUPPLEMENT_TITLE_PATTERNS: List[Tuple[re.Pattern[str], float]] = [
+    (re.compile(r"\btitle\s+page\b"), 3.0),
+    (re.compile(r"\bcopyright\b"), 2.4),
+    (re.compile(r"\btable\s+of\s+contents\b"), 2.8),
+    (re.compile(r"\bcontents\b"), 2.0),
+    (re.compile(r"\backnowledg(e)?ments?\b"), 2.0),
+    (re.compile(r"\bdedication\b"), 2.0),
+    (re.compile(r"\babout\s+the\s+author(s)?\b"), 2.4),
+    (re.compile(r"\balso\s+by\b"), 2.0),
+    (re.compile(r"\bpraise\s+for\b"), 2.0),
+    (re.compile(r"\bcolophon\b"), 2.2),
+    (re.compile(r"\bpublication\s+data\b"), 2.2),
+    (re.compile(r"\btranscriber'?s?\s+note\b"), 2.2),
+    (re.compile(r"\bglossary\b"), 2.2),
+    (re.compile(r"\bindex\b"), 2.0),
+    (re.compile(r"\bbibliograph(y|ies)\b"), 2.0),
+    (re.compile(r"\breferences\b"), 1.8),
+    (re.compile(r"\bappendix\b"), 1.9),
+]
+
+_CONTENT_TITLE_PATTERNS: List[re.Pattern[str]] = [
+    re.compile(r"\bchapter\b"),
+    re.compile(r"\bbook\b"),
+    re.compile(r"\bpart\b"),
+    re.compile(r"\bsection\b"),
+    re.compile(r"\bscene\b"),
+    re.compile(r"\bprologue\b"),
+    re.compile(r"\bepilogue\b"),
+    re.compile(r"\bintroduction\b"),
+    re.compile(r"\bstory\b"),
+]
+
+_SUPPLEMENT_TEXT_KEYWORDS: List[Tuple[str, float]] = [
+    ("copyright", 1.2),
+    ("all rights reserved", 1.1),
+    ("isbn", 0.9),
+    ("library of congress", 1.0),
+    ("table of contents", 1.0),
+    ("dedicated to", 0.8),
+    ("acknowledg", 0.8),
+    ("printed in", 0.6),
+    ("permission", 0.6),
+    ("publisher", 0.5),
+    ("praise for", 0.9),
+    ("also by", 0.9),
+    ("glossary", 0.8),
+    ("index", 0.8),
+    ("newsletter", 3.2),
+    ("mailing list", 2.6),
+    ("sign-up", 2.2),
+]
+
+
+def supplement_score(title: str, text: str, index: int) -> float:
+    """Return a score indicating how likely *title*/*text* is a supplement.
+
+    Higher values ⇒ more likely to be non-story material (title page,
+    copyright, acknowledgements, etc.).
+    """
+    normalized_title = (title or "").lower()
+    score = 0.0
+
+    for pattern, weight in _SUPPLEMENT_TITLE_PATTERNS:
+        if pattern.search(normalized_title):
+            score += weight
+
+    for pattern in _CONTENT_TITLE_PATTERNS:
+        if pattern.search(normalized_title):
+            score -= 2.0
+
+    stripped_text = (text or "").strip()
+    length = len(stripped_text)
+    if length <= 150:
+        score += 0.9
+    elif length <= 400:
+        score += 0.6
+    elif length <= 800:
+        score += 0.35
+
+    lowercase_text = stripped_text.lower()
+    for keyword, weight in _SUPPLEMENT_TEXT_KEYWORDS:
+        if keyword in lowercase_text:
+            score += weight
+
+    if index == 0 and score > 0:
+        score += 0.25
+
+    return score
+
+
+def should_preselect_chapter(
+    title: str,
+    text: str,
+    index: int,
+    total_count: int,
+) -> bool:
+    """Return True if the chapter should be *enabled* by default in the form.
+
+    A single chapter is always preselected.  For multi-chapter books, the
+    chapter is preselected when its supplement score is below 1.9.
+    """
+    if total_count <= 1:
+        return True
+    score = supplement_score(title, text, index)
+    return score < 1.9
+
+
+def ensure_at_least_one_chapter_enabled(chapters: List[Dict[str, Any]]) -> None:
+    """Mutate *chapters* in-place so that at least one has ``enabled=True``."""
+    if not chapters:
+        return
+    if any(chapter.get("enabled") for chapter in chapters):
+        return
+    best_index = max(range(len(chapters)), key=lambda idx: chapters[idx].get("characters", 0))
+    chapters[best_index]["enabled"] = True

abogen/domain/chapter_overrides.py

@@ -0,0 +1,92 @@
+from __future__ import annotations
+
+from typing import Any, Dict, List, Optional, Tuple
+
+from abogen.text_extractor import ExtractedChapter
+from abogen.domain.voice_utils import coerce_truthy
+
+
+def apply_chapter_overrides(
+    extracted: List[ExtractedChapter],
+    overrides: List[Dict[str, Any]],
+) -> Tuple[List[ExtractedChapter], Dict[str, str], List[str]]:
+    if not overrides:
+        return [], {}, []
+
+    selected: List[ExtractedChapter] = []
+    metadata_updates: Dict[str, str] = {}
+    diagnostics: List[str] = []
+
+    for position, payload in enumerate(overrides):
+        if not isinstance(payload, dict):
+            diagnostics.append(
+                f"Skipped chapter override at position {position + 1}: unsupported payload type {type(payload).__name__}."
+            )
+            continue
+
+        enabled = coerce_truthy(payload.get("enabled", True))
+        payload["enabled"] = enabled
+        if not enabled:
+            continue
+
+        metadata_payload = payload.get("metadata") or {}
+        if isinstance(metadata_payload, dict):
+            for key, value in metadata_payload.items():
+                if value is None:
+                    continue
+                metadata_updates[str(key)] = str(value)
+
+        base: Optional[ExtractedChapter] = None
+        idx_candidate = payload.get("index")
+        idx_normalized: Optional[int] = None
+        if isinstance(idx_candidate, int):
+            idx_normalized = idx_candidate
+        elif isinstance(idx_candidate, str):
+            try:
+                idx_normalized = int(idx_candidate)
+            except ValueError:
+                idx_normalized = None
+        if idx_normalized is not None and 0 <= idx_normalized < len(extracted):
+            base = extracted[idx_normalized]
+            payload["index"] = idx_normalized
+
+        if base is None:
+            source_title = payload.get("source_title")
+            if isinstance(source_title, str):
+                base = next((chapter for chapter in extracted if chapter.title == source_title), None)
+
+        if base is None:
+            candidate_title = payload.get("title")
+            if isinstance(candidate_title, str):
+                base = next((chapter for chapter in extracted if chapter.title == candidate_title), None)
+
+        text_override = payload.get("text")
+        if text_override is not None:
+            text_value = str(text_override)
+        elif base is not None:
+            text_value = base.text
+        else:
+            diagnostics.append(
+                f"Skipped chapter override at position {position + 1}: no text provided and no matching source chapter found."
+            )
+            continue
+
+        title_override = payload.get("title")
+        if title_override is not None:
+            title_value = str(title_override)
+        elif base is not None:
+            title_value = base.title
+        else:
+            title_value = f"Chapter {position + 1}"
+
+        if base and not payload.get("source_title"):
+            payload["source_title"] = base.title
+
+        payload["title"] = title_value
+        payload["text"] = text_value
+        payload["characters"] = len(text_value)
+        payload.setdefault("order", payload.get("order", position))
+
+        selected.append(ExtractedChapter(title=title_value, text=text_value))
+
+    return selected, metadata_updates, diagnostics

abogen/domain/chapter_titles.py

@@ -0,0 +1,204 @@
+from __future__ import annotations
+
+import re
+from typing import List, Tuple
+
+
+_HEADING_SANITIZE_RE = re.compile(r"[^a-z0-9]+")
+_HEADING_NUMBER_PREFIX_RE = re.compile(
+    r"^\s*(?P<number>(?:\d+|[ivxlcdm]+))(?P<suffix>(?:[\s.:;-].*)?)$",
+    re.IGNORECASE,
+)
+_ACRONYM_ALLOWLIST = {
+    "AI", "API", "CPU", "DIY", "GPU", "HTML", "HTTP", "HTTPS", "ID",
+    "JSON", "MP3", "MP4", "M4B", "NASA", "OCR", "PDF", "SQL", "TV",
+    "TTS", "UK", "UN", "UFO", "OK", "URL", "USA", "US", "VR",
+}
+_ROMAN_NUMERAL_CHARS = frozenset("IVXLCDM")
+_CAPS_WORD_RE = re.compile(r"[A-Z][A-Z0-9'\u2019-]*")
+
+
+def simplify_heading_text(text: str) -> str:
+    raw = str(text or "").strip().lower()
+    if not raw:
+        return ""
+    simplified = _HEADING_SANITIZE_RE.sub("", raw)
+    if simplified.startswith("chapter"):
+        simplified = simplified[7:]
+    return simplified
+
+
+def headings_equivalent(left: str, right: str) -> bool:
+    simple_left = simplify_heading_text(left)
+    simple_right = simplify_heading_text(right)
+    if not simple_left or not simple_right:
+        return False
+    if simple_left == simple_right:
+        return True
+    if simple_right.startswith(simple_left):
+        return True
+    if simple_left.startswith(simple_right):
+        return True
+    if len(simple_left) > 5 and simple_left in simple_right:
+        return True
+    return False
+
+
+def strip_duplicate_heading_line(text: str, heading: str) -> Tuple[str, bool]:
+    source_text = str(text or "")
+    if not source_text:
+        return source_text, False
+    normalized_heading = simplify_heading_text(heading)
+    if not normalized_heading:
+        return source_text, False
+    lines = source_text.splitlines()
+    new_lines: List[str] = []
+    removed = False
+    for line in lines:
+        stripped = line.strip()
+        if not removed and stripped:
+            if headings_equivalent(stripped, heading):
+                removed = True
+                continue
+        new_lines.append(line)
+    if not removed:
+        return source_text, False
+    while new_lines and not new_lines[0].strip():
+        new_lines.pop(0)
+    return "\n".join(new_lines), True
+
+
+def normalize_caps_word(word: str) -> str:
+    upper = word.upper()
+    letters = [char for char in upper if char.isalpha()]
+    if not letters:
+        return word
+    if upper in _ACRONYM_ALLOWLIST:
+        return word
+    if len(letters) <= 1:
+        return word
+    if all(char in _ROMAN_NUMERAL_CHARS for char in letters) and len(letters) <= 7:
+        return word
+
+    parts = re.split(r"(['\-\u2019])", word)
+    normalized_parts: List[str] = []
+    for part in parts:
+        if part in {"'", "-", "\u2019"}:
+            normalized_parts.append(part)
+            continue
+        if not part:
+            continue
+        normalized_parts.append(part[0].upper() + part[1:].lower())
+    return "".join(normalized_parts) or word
+
+
+def normalize_chapter_opening_caps(text: str) -> Tuple[str, bool]:
+    if not text:
+        return text, False
+
+    leading_len = len(text) - len(text.lstrip())
+    leading = text[:leading_len]
+    working = text[leading_len:]
+    if not working:
+        return text, False
+
+    builder: List[str] = []
+    pos = 0
+    changed = False
+
+    while pos < len(working):
+        char = working[pos]
+        if char in "\r\n":
+            builder.append(working[pos:])
+            pos = len(working)
+            break
+        if char.isspace():
+            builder.append(char)
+            pos += 1
+            continue
+        if char.islower():
+            builder.append(working[pos:])
+            pos = len(working)
+            break
+        if not char.isalpha():
+            builder.append(char)
+            pos += 1
+            continue
+
+        match = _CAPS_WORD_RE.match(working, pos)
+        if not match:
+            builder.append(char)
+            pos += 1
+            continue
+
+        word = match.group(0)
+        if any(ch.islower() for ch in word):
+            builder.append(working[pos:])
+            pos = len(working)
+            break
+
+        normalized = normalize_caps_word(word)
+        if normalized != word:
+            changed = True
+        builder.append(normalized)
+        pos = match.end()
+
+    if pos < len(working):
+        builder.append(working[pos:])
+
+    if not changed:
+        return text, False
+
+    return leading + "".join(builder), True
+
+
+def format_spoken_chapter_title(title: str, index: int, apply_prefix: bool) -> str:
+    base = str(title or "").strip()
+    if not base:
+        return f"Chapter {index}" if apply_prefix else ""
+    if not apply_prefix:
+        return base
+    lowered = base.lower()
+    if lowered.startswith("chapter") and (len(lowered) == 7 or not lowered[7].isalpha()):
+        return base
+    match = _HEADING_NUMBER_PREFIX_RE.match(base)
+    if match:
+        number = match.group("number") or ""
+        suffix = match.group("suffix") or ""
+        cleaned_suffix = suffix.lstrip(" .,:;-_ \t\u2013\u2014\u00b7\u2022")
+        if cleaned_suffix:
+            return f"Chapter {number}. {cleaned_suffix}"
+        return f"Chapter {number}"
+    return base
+
+
+def apply_chapter_text_transforms(
+    text: str,
+    *,
+    heading_text: str,
+    raw_title: str,
+    strip_heading: bool,
+    normalize_caps: bool,
+) -> Tuple[str, bool, bool]:
+    """Strip duplicate heading and normalize opening caps.
+
+    Returns ``(text, heading_removed, caps_changed)``.
+    The caller is responsible for state updates (pending flags, logging,
+    dict mutation, ``continue``).
+    """
+    heading_removed = False
+    caps_changed = False
+
+    if strip_heading and heading_text:
+        text, heading_removed = strip_duplicate_heading_line(text, heading_text)
+        if not heading_removed and raw_title:
+            match = _HEADING_NUMBER_PREFIX_RE.match(raw_title)
+            if match:
+                number = match.group("number")
+                if number:
+                    text, heading_removed = strip_duplicate_heading_line(text, number)
+
+    if normalize_caps and text:
+        text, caps_changed = normalize_chapter_opening_caps(text)
+
+    return text, heading_removed, caps_changed

abogen/domain/chunk_utils.py

@@ -0,0 +1,75 @@
+"""Chunk processing utilities.
+
+Functions for grouping chunks, recording override usage, and selecting
+text for TTS synthesis.
+"""
+
+from __future__ import annotations
+
+from collections import defaultdict
+from typing import Any, Dict, Iterable, Mapping, Optional
+
+from abogen.pronunciation_store import increment_usage
+
+
+def safe_int(value: Any, default: int = 0) -> int:
+    try:
+        return int(value)
+    except (TypeError, ValueError):
+        return default
+
+
+def group_chunks_by_chapter(chunks: Iterable[Dict[str, Any]]) -> Dict[int, List[Dict[str, Any]]]:
+    grouped: Dict[int, List[Dict[str, Any]]] = defaultdict(list)
+    for entry in chunks or []:
+        if not isinstance(entry, dict):
+            continue
+        try:
+            chapter_index = int(entry.get("chapter_index", 0))
+        except (TypeError, ValueError):
+            chapter_index = 0
+        grouped[chapter_index].append(dict(entry))
+
+    for chapter_index, items in grouped.items():
+        items.sort(key=lambda payload: safe_int(payload.get("chunk_index")))
+
+    return grouped
+
+
+def record_override_usage(
+    job: Any,
+    usage_counter: Mapping[str, int],
+    token_map: Mapping[str, str],
+) -> None:
+    if not usage_counter:
+        return
+
+    language = getattr(job, "language", "") or "a"
+    for normalized, amount in usage_counter.items():
+        if amount <= 0:
+            continue
+        token_value = token_map.get(normalized, normalized)
+        try:
+            increment_usage(language=language, token=token_value, amount=int(amount))
+        except Exception:  # pragma: no cover - defensive logging
+            job.add_log(f"Failed to record usage for override {token_value}", level="warning")
+
+
+def chunk_text_for_tts(entry: Mapping[str, Any]) -> str:
+    """Choose the best source text for synthesis.
+
+    We must prefer the raw chunk text (``text`` / ``original_text``) so
+    manual/pronunciation overrides can match against the original tokens
+    (e.g. censored words like ``Unfu*k``).  ``normalized_text`` may have
+    already been run through ``normalize_for_pipeline``, which can remove
+    punctuation and prevent overrides from triggering.
+    """
+
+    if not isinstance(entry, Mapping):
+        return ""
+    return str(
+        entry.get("text")
+        or entry.get("original_text")
+        or entry.get("normalized_text")
+        or ""
+    ).strip()

abogen/domain/conversion_engine.py

@@ -0,0 +1,237 @@
+"""Shared TTS iteration loop used by both WebUI and PyQt conversion runners.
+
+The core pattern is identical across both UIs:
+
+    for seg in tts_segments(text, backend, voice, speed, split_pattern, current_time):
+        check_cancel()
+        update_progress(seg)
+        write_audio(seg, sink)
+        accumulate_subtitles(seg)
+
+After the loop, the caller processes accumulated subtitle tokens.
+
+This module provides ``run_tts_segment_loop`` which encapsulates that
+iteration, and ``synthesize_text`` which adds normalization on top —
+the single entry point both UIs should call for text-to-speech.
+"""
+
+from __future__ import annotations
+
+import time
+from dataclasses import dataclass, field
+from typing import Any, Callable, List, Optional, Protocol
+
+from abogen.domain.audio_sink import AudioSink
+from abogen.domain.conversion_pipeline import tts_segments
+from abogen.domain.normalization import TTSContext
+from abogen.domain.progress import calc_etr_str
+from abogen.domain.subtitle_generation import process_subtitle_tokens
+
+
+class CancelChecker(Protocol):
+    """Returns True if conversion has been cancelled."""
+    def __call__(self) -> bool: ...
+
+
+@dataclass
+class SegmentStats:
+    """Running statistics updated per TTS segment."""
+    processed_chars: int = 0
+    current_time: float = 0.0
+    etr_start_time: float = field(default_factory=time.time)
+    total_characters: int = 0
+
+
+@dataclass
+class SegmentInfo:
+    """Read-only info about a TTS segment, passed to on_segment callback."""
+    graphemes: str
+    audio: Any
+    tokens: list
+    duration: float
+    chunk_start: float
+
+
+def run_tts_segment_loop(
+    *,
+    text: str,
+    backend: Any,
+    voice: Any,
+    speed: float,
+    split_pattern: str,
+    stats: SegmentStats,
+    check_cancel: CancelChecker,
+    on_progress: Callable[[int, str], None],
+    chapter_sink: Optional[AudioSink] = None,
+    audio_sink: Optional[AudioSink] = None,
+    preview_callback: Optional[Callable[[str], None]] = None,
+    on_segment: Optional[Callable[[SegmentInfo], None]] = None,
+    subtitle_mode: str = "Disabled",
+    max_subtitle_words: int = 5,
+    lang_code: str = "a",
+    use_spacy_segmentation: bool = False,
+) -> tuple[int, list]:
+    """Run the core TTS segment iteration loop.
+
+    Args:
+        text: Normalized text to synthesize.
+        backend: TTS pipeline instance (Kokoro or Supertonic).
+        voice: Voice name/id for the backend.
+        speed: Speech speed multiplier.
+        split_pattern: Regex pattern used by the TTS engine for sentence splitting.
+        stats: Running character/timing stats (mutated in place).
+        check_cancel: Called each segment; if it returns True, iteration stops.
+        on_progress: Called with (percent, etr_str) after each segment.
+        chapter_sink: Optional audio sink for the current chapter.
+        audio_sink: Optional audio sink for the merged output.
+        preview_callback: Called with a short preview string per segment.
+        on_segment: Called with a SegmentInfo for each segment *before*
+            audio is written.  Useful for callers that need per-segment
+            subtitle processing (e.g. PyQt dual-writer pattern).
+            When provided, the default subtitle accumulation is skipped.
+        subtitle_mode: Subtitle mode string (e.g. "Disabled", "Sentence").
+        max_subtitle_words: Max words per subtitle entry.
+        lang_code: Language code for subtitle processing.
+        use_spacy_segmentation: Whether spaCy sentence boundaries are active.
+
+    Returns:
+        Tuple of (segment_count, accumulated_subtitle_tokens).
+        The caller is responsible for processing subtitle tokens via
+        ``process_subtitle_tokens`` and writing entries to subtitle writers.
+    """
+    local_segments = 0
+    accumulated_tokens: list[dict] = []
+
+    for seg in tts_segments(
+        text,
+        backend=backend,
+        voice=voice,
+        speed=speed,
+        split_pattern=split_pattern,
+        current_time=stats.current_time,
+    ):
+        if check_cancel():
+            break
+
+        local_segments += 1
+        stats.processed_chars += len(seg.graphemes)
+
+        # Progress
+        if stats.total_characters:
+            percent = min(int(stats.processed_chars / stats.total_characters * 100), 99)
+        else:
+            percent = 0 if stats.processed_chars == 0 else 99
+
+        etr_str = calc_etr_str(
+            time.time() - stats.etr_start_time,
+            stats.processed_chars,
+            stats.total_characters,
+        )
+        on_progress(percent, etr_str)
+
+        # Preview / log
+        if preview_callback:
+            preview_callback(seg.graphemes or "[silence]")
+
+        # Per-segment callback (for callers needing segment-level access)
+        if on_segment:
+            info = SegmentInfo(
+                graphemes=seg.graphemes,
+                audio=seg.audio,
+                tokens=list(seg.tokens) if seg.tokens else [],
+                duration=seg.duration,
+                chunk_start=getattr(seg, "chunk_start", stats.current_time),
+            )
+            on_segment(info)
+
+        # Write audio
+        if chapter_sink:
+            chapter_sink.write(seg.audio)
+        if audio_sink:
+            audio_sink.write(seg.audio)
+
+        # Accumulate subtitle tokens (default path; skipped if on_segment handles it)
+        if not on_segment and subtitle_mode != "Disabled" and seg.tokens:
+            accumulated_tokens.extend(seg.tokens)
+
+        # Update timing
+        if audio_sink:
+            stats.current_time += seg.duration
+
+    return local_segments, accumulated_tokens
+
+
+def process_and_write_subtitles(
+    accumulated_tokens: list[dict],
+    subtitle_writer: Any,
+    *,
+    subtitle_mode: str,
+    max_subtitle_words: int,
+    lang_code: str,
+    use_spacy_segmentation: bool,
+    fallback_end_time: float,
+) -> None:
+    """Process accumulated subtitle tokens and write entries to a subtitle writer.
+
+    This is the standard subtitle post-processing step shared by both UIs.
+    """
+    if not accumulated_tokens or not subtitle_writer:
+        return
+    new_entries: list[tuple] = []
+    process_subtitle_tokens(
+        accumulated_tokens,
+        new_entries,
+        max_subtitle_words,
+        subtitle_mode,
+        lang_code,
+        use_spacy_segmentation=use_spacy_segmentation,
+        fallback_end_time=fallback_end_time,
+    )
+    for start, end, text in new_entries:
+        subtitle_writer.write_entry(start=start, end=end, text=text)
+
+
+def synthesize_text(
+    *,
+    text: str,
+    tts_context: TTSContext,
+    backend: Any,
+    voice: Any,
+    speed: float,
+    stats: SegmentStats,
+    check_cancel: CancelChecker,
+    on_progress: Callable[[int, str], None],
+    chapter_sink: Optional[AudioSink] = None,
+    audio_sink: Optional[AudioSink] = None,
+    preview_callback: Optional[Callable[[str], None]] = None,
+    on_segment: Optional[Callable[[SegmentInfo], None]] = None,
+    subtitle_mode: str = "Disabled",
+    max_subtitle_words: int = 5,
+    lang_code: str = "a",
+    use_spacy_segmentation: bool = False,
+    split_pattern_override: Optional[str] = None,
+) -> tuple[int, list]:
+    """Normalize text and run TTS — the single entry point for both UIs.
+
+    Combines TTSContext.normalize() + run_tts_segment_loop() into one call.
+    UI-specific concerns (provider resolution, progress display) stay in the UI.
+    """
+    normalized = tts_context.normalize(text)
+    return run_tts_segment_loop(
+        text=normalized,
+        backend=backend,
+        voice=voice,
+        speed=speed,
+        split_pattern=split_pattern_override or tts_context.split_pattern,
+        stats=stats,
+        check_cancel=check_cancel,
+        on_progress=on_progress,
+        chapter_sink=chapter_sink,
+        audio_sink=audio_sink,
+        preview_callback=preview_callback,
+        on_segment=on_segment,
+        subtitle_mode=subtitle_mode,
+        max_subtitle_words=max_subtitle_words,
+        lang_code=lang_code,
+        use_spacy_segmentation=use_spacy_segmentation,
+    )

abogen/domain/conversion_pipeline.py

@@ -0,0 +1,242 @@
+"""Shared TTS emission pipeline.
+
+Provides the core TTS emission loop used by both WebUI and PyQt conversion runners.
+The caller handles audio I/O, progress reporting, and subtitle writing.
+"""
+
+from __future__ import annotations
+
+import logging
+from dataclasses import dataclass, field
+from typing import Any, Callable, Dict, Iterator, List, Optional
+
+import numpy as np
+
+from abogen.domain.audio_helpers import to_float32
+from abogen.domain.normalization import prepare_text_for_tts
+from abogen.domain.tokens import FakeToken
+from abogen.domain.audio_buffer import SAMPLE_RATE
+
+logger = logging.getLogger(__name__)
+
+
+@dataclass
+class SegmentResult:
+    """One TTS segment emitted by the pipeline."""
+    graphemes: str
+    audio: np.ndarray
+    duration: float
+    chunk_start: float
+    tokens: List[Dict[str, Any]] = field(default_factory=list)
+
+
+def tts_segments(
+    text: str,
+    *,
+    backend: Any,
+    voice: Any,
+    speed: float,
+    split_pattern: str,
+    current_time: float = 0.0,
+) -> Iterator[SegmentResult]:
+    """Invoke TTS backend on (already normalized) text and yield SegmentResults.
+
+    Use this when you've already normalized the text yourself (e.g. after
+    spaCy sentence segmentation). For raw text, use emit_text_segments() instead.
+
+    Args:
+        text: Already-normalized text to synthesize.
+        backend: TTS pipeline callable.
+        voice: Resolved voice.
+        speed: TTS speed multiplier.
+        split_pattern: Regex pattern for sentence splitting.
+        current_time: Current position in the audio timeline (seconds).
+
+    Yields:
+        SegmentResult for each non-empty TTS segment.
+    """
+    segment_iter = backend(
+        text,
+        voice=voice,
+        speed=speed,
+        split_pattern=split_pattern,
+    )
+
+    chunk_start = current_time
+
+    for segment in segment_iter:
+        graphemes_raw = getattr(segment, "graphemes", "") or ""
+        graphemes = graphemes_raw.strip()
+
+        audio = to_float32(getattr(segment, "audio", None))
+        if audio.size == 0:
+            continue
+
+        duration = len(audio) / SAMPLE_RATE
+
+        tokens_list = getattr(segment, "tokens", [])
+        if not tokens_list and graphemes:
+            tokens_list = [FakeToken(graphemes, 0, duration)]
+
+        tokens = [
+            {
+                "start": chunk_start + (tok.start_ts or 0),
+                "end": chunk_start + (tok.end_ts or 0),
+                "text": tok.text,
+                "whitespace": tok.whitespace,
+            }
+            for tok in tokens_list
+        ]
+
+        yield SegmentResult(
+            graphemes=graphemes,
+            audio=audio,
+            duration=duration,
+            chunk_start=chunk_start,
+            tokens=tokens,
+        )
+
+        chunk_start += duration
+
+
+def emit_text_segments(
+    text: str,
+    *,
+    backend: Any,
+    voice: Any,
+    speed: float,
+    split_pattern: str,
+    current_time: float = 0.0,
+    # normalization
+    heteronym_rules: Any = None,
+    pronunciation_rules: Any = None,
+    normalization_overrides: Any = None,
+    usage_counter: Optional[Dict[str, int]] = None,
+) -> Iterator[SegmentResult]:
+    """Normalize text and yield SegmentResults from the TTS backend.
+
+    This is the innermost TTS emission loop shared by both UIs. It handles:
+    1. Text normalization (heteronym + pronunciation rules)
+    2. TTS backend invocation
+    3. Segment iteration with token extraction
+
+    The caller is responsible for:
+    - Writing audio to sinks
+    - Accumulating tokens for subtitle processing
+    - Progress tracking and cancellation
+    - Error handling
+
+    Args:
+        text: Raw text to synthesize.
+        backend: TTS pipeline callable (kokoro or supertonic).
+        voice: Resolved voice for TTS.
+        speed: TTS speed multiplier.
+        split_pattern: Regex pattern for sentence splitting.
+        current_time: Current position in the audio timeline (seconds).
+        heteronym_rules: Compiled heteronym rules.
+        pronunciation_rules: Compiled pronunciation rules.
+        normalization_overrides: User normalization overrides.
+        usage_counter: Counter for normalization statistics.
+
+    Yields:
+        SegmentResult for each non-empty TTS segment.
+    """
+    source_text = str(text or "")
+    normalized = prepare_text_for_tts(
+        source_text,
+        heteronym_rules=heteronym_rules,
+        pronunciation_rules=pronunciation_rules,
+        normalization_overrides=normalization_overrides,
+        usage_counter=usage_counter,
+    )
+
+    yield from tts_segments(
+        normalized,
+        backend=backend,
+        voice=voice,
+        speed=speed,
+        split_pattern=split_pattern,
+        current_time=current_time,
+    )
+
+
+def emit_text_to_sinks(
+    text: str,
+    *,
+    backend: Any,
+    voice: Any,
+    speed: float,
+    split_pattern: str,
+    current_time: float = 0.0,
+    # sinks
+    audio_sink: Any = None,
+    chapter_sink: Any = None,
+    # subtitle
+    subtitle_writer: Any = None,
+    subtitle_mode: str = "Disabled",
+    subtitle_lang: str = "a",
+    max_subtitle_words: int = 50,
+    use_spacy_segmentation: bool = True,
+    # normalization
+    heteronym_rules: Any = None,
+    pronunciation_rules: Any = None,
+    normalization_overrides: Any = None,
+    usage_counter: Optional[Dict[str, int]] = None,
+) -> tuple[int, float, List[Dict[str, Any]]]:
+    """Emit TTS audio for text, writing to sinks and collecting subtitle tokens.
+
+    Convenience wrapper around emit_text_segments() that handles audio writing
+    and token accumulation. Returns stats for the caller to update progress.
+
+    Returns:
+        Tuple of (segments_emitted, new_current_time, accumulated_tokens).
+    """
+    from abogen.domain.subtitle_generation import process_subtitle_tokens
+
+    segments_emitted = 0
+    accumulated_tokens: List[Dict[str, Any]] = []
+
+    for seg in emit_text_segments(
+        text,
+        backend=backend,
+        voice=voice,
+        speed=speed,
+        split_pattern=split_pattern,
+        current_time=current_time,
+        heteronym_rules=heteronym_rules,
+        pronunciation_rules=pronunciation_rules,
+        normalization_overrides=normalization_overrides,
+        usage_counter=usage_counter,
+    ):
+        segments_emitted += 1
+
+        # Write audio
+        if chapter_sink:
+            chapter_sink.write(seg.audio)
+        if audio_sink:
+            audio_sink.write(seg.audio)
+
+        # Collect tokens
+        accumulated_tokens.extend(seg.tokens)
+
+    # Flush subtitle tokens
+    if subtitle_writer and accumulated_tokens:
+        _use_spacy = subtitle_mode not in ("Disabled", "Line")
+        new_entries: List[tuple] = []
+        process_subtitle_tokens(
+            accumulated_tokens,
+            new_entries,
+            max_subtitle_words,
+            subtitle_mode,
+            subtitle_lang,
+            use_spacy_segmentation=_use_spacy,
+            fallback_end_time=current_time + sum(t["end"] - t["start"] for t in accumulated_tokens if accumulated_tokens),
+        )
+        for start, end, text_entry in new_entries:
+            subtitle_writer.write_entry(start=start, end=end, text=text_entry)
+
+    new_time = current_time
+    if accumulated_tokens:
+        new_time = max(t["end"] for t in accumulated_tokens)
+
+    return segments_emitted, new_time, accumulated_tokens

abogen/domain/device.py

@@ -0,0 +1,31 @@
+from __future__ import annotations
+
+import platform as _platform
+
+
+def select_device() -> str:
+    """Return the best available compute device (``"mps"``, ``"cuda"``, or ``"cpu"``).
+
+    Checks ``torch`` availability at runtime so this can be called from
+    any context without requiring torch at import time.
+    """
+    try:
+        import torch  # type: ignore[import-not-found]
+    except Exception:
+        return "cpu"
+
+    system = _platform.system()
+    if system == "Darwin" and _platform.processor() == "arm":
+        try:
+            if torch.backends.mps.is_available():  # type: ignore[union-attr]
+                return "mps"
+        except Exception:
+            pass
+        return "cpu"
+
+    try:
+        if torch.cuda.is_available():  # type: ignore[union-attr]
+            return "cuda"
+    except Exception:
+        pass
+    return "cpu"

abogen/domain/file_type.py

@@ -0,0 +1,136 @@
+from __future__ import annotations
+
+import re
+from dataclasses import dataclass
+from pathlib import Path
+from typing import Any, Dict, List, Tuple
+
+from abogen.text_extractor import ExtractedChapter
+
+
+_SIGNIFICANT_LENGTH_THRESHOLDS: Dict[str, int] = {"epub": 1000, "markdown": 500}
+_MIN_SHORT_CONTENT: Dict[str, int] = {"epub": 240, "markdown": 160}
+_STRUCTURAL_KEYWORDS = (
+    "preface",
+    "prologue",
+    "introduction",
+    "foreword",
+    "epilogue",
+    "afterword",
+    "appendix",
+    "acknowledgment",
+    "acknowledgement",
+)
+_STRUCTURAL_MIN_LENGTH = 120
+_MAX_SHORT_CHAPTERS = 2
+
+
+@dataclass
+class ChapterFilterResult:
+    kept: List[ExtractedChapter]
+    skipped: List[Tuple[str, int]]
+
+
+def infer_file_type(path: Path) -> str:
+    suffix = path.suffix.lower()
+    if suffix == ".epub":
+        return "epub"
+    if suffix in {".md", ".markdown"}:
+        return "markdown"
+    if suffix == ".pdf":
+        return "pdf"
+    if suffix == ".txt":
+        return "text"
+    return suffix.lstrip(".") or "text"
+
+
+def looks_structural(title: str) -> bool:
+    lowered = title.strip().lower()
+    if not lowered:
+        return False
+    return any(keyword in lowered for keyword in _STRUCTURAL_KEYWORDS)
+
+
+def chapter_label(file_type: str) -> str:
+    return "chapters" if file_type.lower() in {"epub", "markdown"} else "pages"
+
+
+def auto_select_relevant_chapters(
+    chapters: List[ExtractedChapter],
+    file_type: str,
+) -> ChapterFilterResult:
+    if not chapters:
+        return ChapterFilterResult(kept=[], skipped=[])
+
+    normalized = file_type.lower()
+    threshold = _SIGNIFICANT_LENGTH_THRESHOLDS.get(normalized, 0)
+    min_short = _MIN_SHORT_CONTENT.get(normalized, 0)
+
+    kept: List[ExtractedChapter] = []
+    skipped: List[Tuple[str, int]] = []
+    short_kept = 0
+
+    for chapter in chapters:
+        stripped = chapter.text.strip()
+        length = len(stripped)
+        if length == 0:
+            skipped.append((chapter.title, length))
+            continue
+
+        keep = False
+        if threshold == 0:
+            keep = True
+        elif length >= threshold:
+            keep = True
+        elif not kept:
+            keep = True
+        elif min_short and length >= min_short and short_kept < _MAX_SHORT_CHAPTERS:
+            keep = True
+            short_kept += 1
+        elif looks_structural(chapter.title) and length >= _STRUCTURAL_MIN_LENGTH:
+            keep = True
+
+        if keep:
+            kept.append(chapter)
+        else:
+            skipped.append((chapter.title, length))
+
+    if kept:
+        return ChapterFilterResult(kept=kept, skipped=skipped)
+
+    longest_idx = None
+    longest_length = 0
+    for idx, chapter in enumerate(chapters):
+        stripped = chapter.text.strip()
+        if stripped and len(stripped) > longest_length:
+            longest_length = len(stripped)
+            longest_idx = idx
+
+    if longest_idx is not None:
+        longest = chapters[longest_idx]
+        fallback_skipped = [
+            (chapter.title, len(chapter.text.strip()))
+            for idx, chapter in enumerate(chapters)
+            if idx != longest_idx and chapter.text.strip()
+        ]
+        return ChapterFilterResult(kept=[longest], skipped=fallback_skipped)
+
+    return ChapterFilterResult(kept=[], skipped=skipped)
+
+
+def update_metadata_for_chapter_count(
+    metadata: Dict[str, Any], count: int, file_type: str
+) -> None:
+    if not metadata or count <= 0:
+        return
+
+    label = "Chapters" if file_type.lower() in {"epub", "markdown"} else "Pages"
+    metadata["chapter_count"] = str(count)
+
+    pattern = re.compile(r"\(\d+\s+(Chapters?|Pages?)\)")
+    replacement = f"({count} {label})"
+    for key in ("album", "ALBUM"):
+        value = metadata.get(key)
+        if not isinstance(value, str):
+            continue
+        metadata[key] = pattern.sub(replacement, value)

abogen/domain/intro_outro.py

@@ -0,0 +1,83 @@
+"""Intro/outro text building and voice resolution for audiobook conversion.
+
+Both UIs (WebUI and Desktop) need to:
+1. Build intro/outro text from book metadata
+2. Resolve which voice to use for intro/outro synthesis
+
+This module provides the shared domain logic. The actual TTS synthesis
+and audio writing remain UI-specific.
+"""
+
+from __future__ import annotations
+
+from dataclasses import dataclass
+from typing import Any, Dict, Optional
+
+from abogen.domain.title_builder import build_title_intro_text, build_outro_text
+from abogen.domain.voice_resolution import resolve_fallback_voice_spec
+
+
+@dataclass
+class IntroOutroSpec:
+    """Resolved intro or outro specification ready for TTS synthesis."""
+    text: str
+    voice_spec: str
+    enabled: bool
+
+
+def resolve_intro(
+    metadata: Optional[Dict[str, Any]],
+    original_filename: str,
+    read_title_intro: bool,
+    base_voice_spec: str,
+    job_voice: str,
+    voice_cache_keys: list[str],
+) -> IntroOutroSpec:
+    """Resolve the intro specification from job settings and metadata.
+
+    Returns an IntroOutroSpec with text and voice_spec populated,
+    or enabled=False if intro is disabled or text cannot be built.
+    """
+    if not read_title_intro:
+        return IntroOutroSpec(text="", voice_spec="", enabled=False)
+
+    text = build_title_intro_text(metadata, original_filename)
+    if not text:
+        return IntroOutroSpec(text="", voice_spec="", enabled=False)
+
+    voice_spec = resolve_fallback_voice_spec(
+        base_voice_spec, job_voice, voice_cache_keys
+    )
+    if not voice_spec:
+        return IntroOutroSpec(text=text, voice_spec="", enabled=False)
+
+    return IntroOutroSpec(text=text, voice_spec=voice_spec, enabled=True)
+
+
+def resolve_outro(
+    metadata: Optional[Dict[str, Any]],
+    original_filename: str,
+    read_closing_outro: bool,
+    base_voice_spec: str,
+    job_voice: str,
+    voice_cache_keys: list[str],
+) -> IntroOutroSpec:
+    """Resolve the outro specification from job settings and metadata.
+
+    Returns an IntroOutroSpec with text and voice_spec populated,
+    or enabled=False if outro is disabled or text cannot be built.
+    """
+    if not read_closing_outro:
+        return IntroOutroSpec(text="", voice_spec="", enabled=False)
+
+    text = build_outro_text(metadata, original_filename)
+    if not text:
+        return IntroOutroSpec(text="", voice_spec="", enabled=False)
+
+    voice_spec = resolve_fallback_voice_spec(
+        base_voice_spec, job_voice, voice_cache_keys
+    )
+    if not voice_spec:
+        return IntroOutroSpec(text=text, voice_spec="", enabled=False)
+
+    return IntroOutroSpec(text=text, voice_spec=voice_spec, enabled=True)

abogen/domain/metadata_extraction.py

@@ -0,0 +1,504 @@
+"""Metadata extraction and processing utilities.
+
+This module provides functions for extracting metadata from text content,
+formatting metadata tags for TTS embedding, and generating ffmpeg metadata arguments.
+"""
+
+from __future__ import annotations
+
+import datetime
+import logging
+import os
+import re
+import uuid
+from pathlib import Path
+from typing import Any, Dict, List, Optional, Tuple
+
+logger = logging.getLogger(__name__)
+
+
+def extract_metadata_from_text(text: str) -> Dict[str, Optional[str]]:
+    """Extract metadata tags from text content.
+    
+    Looks for tags in format: <<METADATA_KEY:value>>
+    
+    Supported tags:
+    - TITLE, ARTIST, ALBUM, YEAR
+    - ALBUM_ARTIST, COMPOSER, GENRE
+    - COVER_PATH
+    
+    Args:
+        text: Text content to search for metadata tags.
+        
+    Returns:
+        Dictionary with extracted metadata values (None if not found).
+    """
+    metadata = {}
+    
+    patterns = {
+        "title": r"<<METADATA_TITLE:([^>]*)>>",
+        "artist": r"<<METADATA_ARTIST:([^>]*)>>",
+        "album": r"<<METADATA_ALBUM:([^>]*)>>",
+        "year": r"<<METADATA_YEAR:([^>]*)>>",
+        "album_artist": r"<<METADATA_ALBUM_ARTIST:([^>]*)>>",
+        "composer": r"<<METADATA_COMPOSER:([^>]*)>>",
+        "genre": r"<<METADATA_GENRE:([^>]*)>>",
+        "cover_path": r"<<METADATA_COVER_PATH:([^>]*)>>",
+    }
+    
+    for key, pattern in patterns.items():
+        match = re.search(pattern, text)
+        if match:
+            metadata[key] = match.group(1).strip()
+        else:
+            metadata[key] = None
+    
+    return metadata
+
+
+def get_filename_from_path(
+    file_path: str,
+    display_path: Optional[str] = None,
+    from_queue: bool = False,
+) -> str:
+    """Extract filename (without extension) from path.
+    
+    Args:
+        file_path: The file path to extract from.
+        display_path: Optional display path (used if from_queue is False).
+        from_queue: Whether the file is from queue.
+        
+    Returns:
+        Filename without extension.
+    """
+    if from_queue:
+        base_path = file_path
+    else:
+        base_path = display_path if display_path else file_path
+    
+    filename = os.path.splitext(os.path.basename(base_path))[0]
+    return filename
+
+
+def build_ffmpeg_metadata_args(
+    metadata: Dict[str, Optional[str]],
+    filename: str,
+) -> List[str]:
+    """Build ffmpeg metadata arguments from metadata dictionary.
+    
+    Args:
+        metadata: Dictionary with metadata keys and values.
+        filename: Fallback filename for title/album if not specified.
+        
+    Returns:
+        List of ffmpeg metadata arguments.
+    """
+    args = []
+    
+    # Default values
+    defaults = {
+        "title": filename,
+        "artist": "Unknown",
+        "album": filename,
+        "date": str(datetime.datetime.now().year),
+        "album_artist": "Unknown",
+        "composer": "Narrator",
+        "genre": "Audiobook",
+    }
+    
+    # Map of metadata keys to ffmpeg metadata keys
+    key_mapping = {
+        "title": "title",
+        "artist": "artist",
+        "album": "album",
+        "year": "date",  # year -> date for ffmpeg
+        "album_artist": "album_artist",
+        "composer": "composer",
+        "genre": "genre",
+    }
+    
+    for metadata_key, ffmpeg_key in key_mapping.items():
+        value = metadata.get(metadata_key)
+        if value is None:
+            value = defaults.get(metadata_key, "")
+        if value:
+            args.extend(["-metadata", f"{ffmpeg_key}={value}"])
+    
+    return args
+
+
+def extract_metadata_and_build_args(
+    text: str,
+    filename: str,
+    display_path: Optional[str] = None,
+    from_queue: bool = False,
+) -> Tuple[List[str], Optional[str]]:
+    """Extract metadata from text and build ffmpeg arguments.
+    
+    Convenience function that combines extract_metadata_from_text and
+    build_ffmpeg_metadata_args.
+    
+    Args:
+        text: Text content to search for metadata tags.
+        filename: Fallback filename for title/album.
+        display_path: Optional display path.
+        from_queue: Whether the file is from queue.
+        
+    Returns:
+        Tuple of (ffmpeg_metadata_args, cover_path).
+    """
+    metadata = extract_metadata_from_text(text)
+    cover_path = metadata.get("cover_path")
+    
+    # Get actual filename from path
+    actual_filename = get_filename_from_path(
+        file_path=filename,
+        display_path=display_path,
+        from_queue=from_queue,
+    )
+    
+    args = build_ffmpeg_metadata_args(metadata, actual_filename)
+    return args, cover_path
+
+
+def read_text_for_metadata(
+    file_path: str,
+    is_direct_text: bool,
+    direct_text: Optional[str] = None,
+    encoding: Optional[str] = None,
+) -> str:
+    """Read text content for metadata extraction.
+    
+    Args:
+        file_path: Path to file (or text if is_direct_text).
+        is_direct_text: Whether file_path contains direct text.
+        direct_text: Optional direct text (used if is_direct_text).
+        encoding: File encoding (detected if not provided).
+        
+    Returns:
+        Text content for metadata extraction.
+    """
+    if is_direct_text:
+        return direct_text or file_path
+    
+    # Read from file
+    actual_path = direct_text if direct_text else file_path
+    
+    try:
+        if encoding is None:
+            from abogen.utils import detect_encoding
+            encoding = detect_encoding(actual_path)
+        
+        with open(actual_path, "r", encoding=encoding, errors="replace") as f:
+            return f.read()
+    except Exception:
+        return ""
+
+
+def extract_metadata_for_file(
+    file_path: str,
+    is_direct_text: bool = False,
+) -> Dict[str, Optional[str]]:
+    """Extract metadata dict from a file or direct text.
+
+    Convenience function combining read_text_for_metadata + extract_metadata_from_text.
+    Returns empty dict on any error.
+    """
+    try:
+        text = read_text_for_metadata(
+            file_path=file_path,
+            is_direct_text=is_direct_text,
+            direct_text=file_path if is_direct_text else None,
+        )
+        if text:
+            return extract_metadata_from_text(text) or {}
+    except Exception:
+        pass
+    return {}
+
+
+def format_metadata_tags(
+    metadata: Dict[str, Any],
+    filename: str,
+    chapter_count: int,
+    file_type: str,
+    cover_bytes: Optional[bytes] = None,
+    cache_dir: Optional[str] = None,
+) -> str:
+    """Format metadata tags for insertion into TTS text.
+
+    Builds <<METADATA_KEY:value>> tags that are later parsed by
+    extract_metadata_from_text() and fed to ffmpeg.
+
+    Args:
+        metadata: Dict with keys like 'title', 'authors' (list),
+            'publication_year', 'description', 'cover_image' (bytes).
+        filename: Fallback filename (without extension) for title/album.
+        chapter_count: Number of chapters/pages.
+        file_type: 'epub', 'pdf', or 'markdown'.
+        cover_bytes: Optional cover image bytes to save to cache.
+        cache_dir: Directory for cover cache (uses default if None).
+
+    Returns:
+        Newline-joined string of <<METADATA_KEY:value>> tags.
+    """
+    title = metadata.get("title") or filename
+    authors = metadata.get("authors") or ["Unknown"]
+    authors_text = ", ".join(authors) if isinstance(authors, list) else str(authors)
+    year = metadata.get("publication_year") or str(datetime.datetime.now().year)
+
+    chapter_label = "Chapters" if file_type in ("epub", "markdown") else "Pages"
+    chapter_text = f"{chapter_count} {chapter_label}"
+
+    tags = [
+        f"<<METADATA_TITLE:{title}>>",
+        f"<<METADATA_ARTIST:{authors_text}>>",
+        f"<<METADATA_ALBUM:{title} ({chapter_text})>>",
+        f"<<METADATA_YEAR:{year}>>",
+        f"<<METADATA_ALBUM_ARTIST:{authors_text}>>",
+        f"<<METADATA_COMPOSER:Narrator>>",
+        f"<<METADATA_GENRE:Audiobook>>",
+    ]
+
+    cover_path = _save_cover_to_cache(cover_bytes, cache_dir)
+    if cover_path:
+        tags.append(f"<<METADATA_COVER_PATH:{cover_path}>>")
+
+    return "\n".join(tags)
+
+
+def _save_cover_to_cache(
+    cover_bytes: Optional[bytes],
+    cache_dir: Optional[str] = None,
+) -> Optional[str]:
+    """Save cover image bytes to cache directory.
+
+    Args:
+        cover_bytes: Raw image bytes (e.g. JPEG/PNG).
+        cache_dir: Directory to save to. If None, returns None.
+
+    Returns:
+        Normalized path to saved cover file, or None on failure.
+    """
+    if not cover_bytes:
+        return None
+    if cache_dir is None:
+        return None
+
+    try:
+        cover_path = os.path.join(cache_dir, f"cover_{uuid.uuid4()}.jpg")
+        cover_path = os.path.normpath(cover_path)
+        with open(cover_path, "wb") as f:
+            f.write(cover_bytes)
+        return cover_path
+    except Exception as e:
+        logger.warning("Failed to save cover image: %s", e)
+        return None
+
+
+def extract_book_metadata_epub(book: Any) -> Dict[str, Any]:
+    """Extract metadata from an opened ebooklib EPUB book.
+
+    Args:
+        book: An opened ebooklib EPUB book object.
+
+    Returns:
+        Dict with keys: title, authors, description, publisher,
+        publication_year, cover_image (bytes or None).
+    """
+    import ebooklib
+
+    metadata: Dict[str, Any] = {
+        "title": None,
+        "authors": [],
+        "description": None,
+        "cover_image": None,
+        "publisher": None,
+        "publication_year": None,
+    }
+
+    try:
+        title_items = book.get_metadata("DC", "title")
+        if title_items and len(title_items) > 0:
+            metadata["title"] = title_items[0][0]
+    except Exception as e:
+        logger.warning("Error extracting title metadata: %s", e)
+
+    try:
+        author_items = book.get_metadata("DC", "creator")
+        if author_items:
+            metadata["authors"] = [
+                author[0] for author in author_items if len(author) > 0
+            ]
+    except Exception as e:
+        logger.warning("Error extracting author metadata: %s", e)
+
+    try:
+        desc_items = book.get_metadata("DC", "description")
+        if desc_items and len(desc_items) > 0:
+            metadata["description"] = desc_items[0][0]
+    except Exception as e:
+        logger.warning("Error extracting description metadata: %s", e)
+
+    try:
+        publisher_items = book.get_metadata("DC", "publisher")
+        if publisher_items and len(publisher_items) > 0:
+            metadata["publisher"] = publisher_items[0][0]
+    except Exception as e:
+        logger.warning("Error extracting publisher metadata: %s", e)
+
+    try:
+        date_items = book.get_metadata("DC", "date")
+        if date_items and len(date_items) > 0:
+            date_str = date_items[0][0]
+            year_match = re.search(r"\b(19|20)\d{2}\b", date_str)
+            if year_match:
+                metadata["publication_year"] = year_match.group(0)
+            else:
+                metadata["publication_year"] = date_str
+    except Exception as e:
+        logger.warning("Error extracting publication date metadata: %s", e)
+
+    for item in book.get_items_of_type(ebooklib.ITEM_COVER):
+        metadata["cover_image"] = item.get_content()
+        break
+
+    if not metadata["cover_image"]:
+        for item in book.get_items_of_type(ebooklib.ITEM_IMAGE):
+            if "cover" in item.get_name().lower():
+                metadata["cover_image"] = item.get_content()
+                break
+
+    return metadata
+
+
+def extract_book_metadata_pdf(pdf_doc: Any) -> Dict[str, Any]:
+    """Extract metadata from an opened PyMuPDF document.
+
+    Args:
+        pdf_doc: An opened fitz.Document object.
+
+    Returns:
+        Dict with keys: title, authors, description, publisher,
+        publication_year, cover_image (bytes or None).
+    """
+    metadata: Dict[str, Any] = {
+        "title": None,
+        "authors": [],
+        "description": None,
+        "cover_image": None,
+        "publisher": None,
+        "publication_year": None,
+    }
+
+    pdf_info = pdf_doc.metadata
+    if pdf_info:
+        metadata["title"] = pdf_info.get("title", None)
+        author = pdf_info.get("author", None)
+        if author:
+            metadata["authors"] = [author]
+        metadata["description"] = pdf_info.get("subject", None)
+        keywords = pdf_info.get("keywords", None)
+        if keywords:
+            if metadata["description"]:
+                metadata["description"] += f"\n\nKeywords: {keywords}"
+            else:
+                metadata["description"] = f"Keywords: {keywords}"
+        metadata["publisher"] = pdf_info.get("creator", None)
+
+        if "creationDate" in pdf_info:
+            date_str = pdf_info["creationDate"]
+            year_match = re.search(r"D:(\d{4})", date_str)
+            if year_match:
+                metadata["publication_year"] = year_match.group(1)
+        elif "modDate" in pdf_info:
+            date_str = pdf_info["modDate"]
+            year_match = re.search(r"D:(\d{4})", date_str)
+            if year_match:
+                metadata["publication_year"] = year_match.group(1)
+
+    if len(pdf_doc) > 0:
+        try:
+            import fitz
+            pix = pdf_doc[0].get_pixmap(matrix=fitz.Matrix(2, 2))
+            metadata["cover_image"] = pix.tobytes("png")
+        except Exception:
+            pass
+
+    return metadata
+
+
+def extract_book_metadata_markdown(
+    markdown_text: str,
+    markdown_toc: Optional[List[Dict[str, Any]]] = None,
+) -> Dict[str, Any]:
+    """Extract metadata from markdown frontmatter and first heading.
+
+    Args:
+        markdown_text: Raw markdown text content.
+        markdown_toc: Optional table of contents list (each item has
+            'level' and 'name' keys).
+
+    Returns:
+        Dict with keys: title, authors, description, publication_year.
+        cover_image is always None for markdown.
+    """
+    metadata: Dict[str, Any] = {
+        "title": None,
+        "authors": [],
+        "description": None,
+        "cover_image": None,
+        "publisher": None,
+        "publication_year": None,
+    }
+
+    if not markdown_text:
+        return metadata
+
+    frontmatter_match = re.match(
+        r"^---\s*\n(.*?)\n---\s*\n", markdown_text, re.DOTALL
+    )
+    if frontmatter_match:
+        try:
+            frontmatter = frontmatter_match.group(1)
+            title_match = re.search(
+                r"^title:\s*(.+)$", frontmatter, re.MULTILINE | re.IGNORECASE
+            )
+            if title_match:
+                metadata["title"] = title_match.group(1).strip().strip("\"'")
+
+            author_match = re.search(
+                r"^author:\s*(.+)$", frontmatter, re.MULTILINE | re.IGNORECASE
+            )
+            if author_match:
+                metadata["authors"] = [
+                    author_match.group(1).strip().strip("\"'")
+                ]
+
+            desc_match = re.search(
+                r"^description:\s*(.+)$", frontmatter, re.MULTILINE | re.IGNORECASE
+            )
+            if desc_match:
+                metadata["description"] = (
+                    desc_match.group(1).strip().strip("\"'")
+                )
+
+            date_match = re.search(
+                r"^date:\s*(.+)$", frontmatter, re.MULTILINE | re.IGNORECASE
+            )
+            if date_match:
+                date_str = date_match.group(1).strip().strip("\"'")
+                year_match = re.search(r"\b(19|20)\d{2}\b", date_str)
+                if year_match:
+                    metadata["publication_year"] = year_match.group(0)
+        except Exception as e:
+            logger.warning("Error parsing markdown frontmatter: %s", e)
+
+    if not metadata["title"] and markdown_toc:
+        first_h1 = next(
+            (h for h in markdown_toc if h.get("level") == 1), None
+        )
+        if first_h1:
+            metadata["title"] = first_h1.get("name")
+
+    return metadata

abogen/domain/metadata_helpers.py

@@ -0,0 +1,405 @@
+from __future__ import annotations
+
+import json
+import math
+import re
+from pathlib import Path
+from typing import Any, Dict, List, Mapping, Optional, Tuple
+
+
+_SERIES_NAME_KEYS = (
+    "series",
+    "series_name",
+    "series_title",
+)
+_SERIES_NUMBER_KEYS = (
+    "series_index",
+    "series_position",
+    "series_sequence",
+    "book_number",
+    "series_number",
+)
+_SERIES_NUMBER_RE = re.compile(r"\d+(?:\.\d+)?")
+
+
+def normalize_metadata_map(values: Optional[Mapping[str, Any]]) -> Dict[str, str]:
+    normalized: Dict[str, str] = {}
+    if not values:
+        return normalized
+    for key, value in values.items():
+        if value is None:
+            continue
+        text = str(value).strip()
+        if not text:
+            continue
+        normalized[str(key).casefold()] = text
+    return normalized
+
+
+def format_author_sentence(raw: Optional[str]) -> str:
+    if raw is None:
+        return ""
+    normalized = str(raw).strip()
+    if not normalized:
+        return ""
+    lowered = normalized.casefold()
+    if lowered in {"unknown", "various"}:
+        return ""
+
+    working = normalized.replace("&", " and ")
+    segments = [segment.strip() for segment in working.split(",") if segment.strip()]
+    tokens: List[str] = []
+
+    if segments:
+        for segment in segments:
+            parts = [part.strip() for part in re.split(r"\band\b", segment, flags=re.IGNORECASE) if part.strip()]
+            if parts:
+                tokens.extend(parts)
+            else:
+                tokens.append(segment)
+    else:
+        parts = [part.strip() for part in re.split(r"\band\b", working, flags=re.IGNORECASE) if part.strip()]
+        tokens.extend(parts or [normalized])
+
+    cleaned = [token for token in tokens if token and token.casefold() not in {"unknown", "various"}]
+    if not cleaned:
+        return ""
+    if len(cleaned) == 1:
+        return f"By {cleaned[0]}"
+    if len(cleaned) == 2:
+        return f"By {cleaned[0]} and {cleaned[1]}"
+    return f"By {', '.join(cleaned[:-1])}, and {cleaned[-1]}"
+
+
+def ensure_sentence(text: str) -> str:
+    cleaned = text.strip()
+    if not cleaned:
+        return ""
+    if cleaned[-1] in ".!?":
+        return cleaned
+    return f"{cleaned}."
+
+
+def normalize_series_number(value: Any) -> Optional[str]:
+    text = str(value or "").strip()
+    if not text:
+        return None
+    candidate = text.replace(",", ".")
+    if candidate.replace(".", "", 1).isdigit():
+        if "." in candidate:
+            normalized = candidate.rstrip("0").rstrip(".")
+            return normalized or "0"
+        try:
+            return str(int(candidate))
+        except ValueError:
+            pass
+    match = _SERIES_NUMBER_RE.search(candidate)
+    if not match:
+        return None
+    normalized = match.group(0)
+    if "." in normalized:
+        normalized = normalized.rstrip("0").rstrip(".")
+        return normalized or "0"
+    try:
+        return str(int(normalized))
+    except ValueError:
+        return normalized
+
+
+def extract_series_metadata(values: Mapping[str, str]) -> Tuple[Optional[str], Optional[str]]:
+    series_name: Optional[str] = None
+    for key in _SERIES_NAME_KEYS:
+        raw = values.get(key)
+        if raw:
+            cleaned = str(raw).strip()
+            if cleaned:
+                series_name = cleaned
+                break
+
+    series_number: Optional[str] = None
+    for key in _SERIES_NUMBER_KEYS:
+        raw = values.get(key)
+        if raw is None:
+            continue
+        normalized = normalize_series_number(raw)
+        if normalized:
+            series_number = normalized
+            break
+
+    return series_name, series_number
+
+
+def format_series_sentence(series_name: Optional[str], series_number: Optional[str]) -> str:
+    if not series_name or not series_number:
+        return ""
+    name = series_name.strip()
+    number = series_number.strip()
+    if not name or not number:
+        return ""
+    article = "the " if not name.lower().startswith("the ") else ""
+    phrase = f"Book {number} of {article}{name}"
+    return re.sub(r"\s+", " ", phrase).strip()
+
+
+_PEOPLE_SPLIT_RE = re.compile(r"[;,/&]|\band\b", re.IGNORECASE)
+_LIST_SPLIT_RE = re.compile(r"[;,\n]")
+_SERIES_SEQUENCE_TAG_KEYS: Tuple[str, ...] = (
+    "series_index",
+    "series_position",
+    "series_sequence",
+    "series_number",
+    "seriesnumber",
+    "book_number",
+    "booknumber",
+)
+
+
+def normalize_metadata_casefold(values: Optional[Mapping[str, Any]]) -> Dict[str, Any]:
+    normalized: Dict[str, Any] = {}
+    if not values:
+        return normalized
+    for key, value in values.items():
+        if value is None:
+            continue
+        key_text = str(key).strip().lower()
+        if not key_text:
+            continue
+        if isinstance(value, (list, tuple, set)):
+            normalized[key_text] = value
+        else:
+            text = str(value).strip()
+            if text:
+                normalized[key_text] = text
+    return normalized
+
+
+def split_people_field(raw: Any) -> List[str]:
+    if raw is None:
+        return []
+    if isinstance(raw, (list, tuple, set)):
+        results: List[str] = []
+        for item in raw:
+            results.extend(split_people_field(item))
+        return results
+    text = str(raw or "").strip()
+    if not text:
+        return []
+    tokens = [_token.strip() for _token in _PEOPLE_SPLIT_RE.split(text) if _token.strip()]
+    seen: set[str] = set()
+    ordered: List[str] = []
+    for token in tokens:
+        key = token.casefold()
+        if key in seen:
+            continue
+        seen.add(key)
+        ordered.append(token)
+    return ordered
+
+
+def split_simple_list(raw: Any) -> List[str]:
+    if raw is None:
+        return []
+    if isinstance(raw, (list, tuple, set)):
+        results: List[str] = []
+        for item in raw:
+            results.extend(split_simple_list(item))
+        return results
+    text = str(raw or "").strip()
+    if not text:
+        return []
+    tokens = [_token.strip() for _token in _LIST_SPLIT_RE.split(text) if _token.strip()]
+    seen: set[str] = set()
+    ordered: List[str] = []
+    for token in tokens:
+        key = token.casefold()
+        if key in seen:
+            continue
+        seen.add(key)
+        ordered.append(token)
+    return ordered
+
+
+def first_nonempty(*values: Any) -> Optional[str]:
+    for value in values:
+        if value is None:
+            continue
+        if isinstance(value, (list, tuple, set)):
+            items = list(value)
+            if not items:
+                continue
+            value = items[0]
+        text = str(value).strip()
+        if text:
+            return text
+    return None
+
+
+def extract_year(raw: Optional[str]) -> Optional[int]:
+    if not raw:
+        return None
+    text = str(raw).strip()
+    if not text:
+        return None
+    match = re.search(r"(19|20)\d{2}", text)
+    if match:
+        try:
+            return int(match.group(0))
+        except ValueError:
+            return None
+    try:
+        parsed = int(text)
+    except ValueError:
+        return None
+    if 0 < parsed < 3000:
+        return parsed
+    return None
+
+
+def normalize_series_sequence(raw: Any) -> Optional[str]:
+    if raw is None:
+        return None
+    if isinstance(raw, (int, float)):
+        if isinstance(raw, float) and (math.isnan(raw) or math.isinf(raw)):
+            return None
+        text = str(raw)
+    else:
+        text = str(raw).strip()
+    if not text:
+        return None
+    candidate = text.replace(",", ".")
+    match = _SERIES_NUMBER_RE.search(candidate)
+    if not match:
+        return None
+    normalized = match.group(0)
+    if "." in normalized:
+        normalized = normalized.rstrip("0").rstrip(".")
+        if not normalized:
+            normalized = "0"
+        return normalized
+    try:
+        return str(int(normalized))
+    except ValueError:
+        cleaned = normalized.lstrip("0")
+        return cleaned or "0"
+
+
+def build_audiobookshelf_metadata(
+    tags: Mapping[str, Any],
+    *,
+    language: str = "",
+    filename: str = "",
+) -> Dict[str, Any]:
+    normalized = normalize_metadata_casefold(tags)
+    title = first_nonempty(
+        normalized.get("title"),
+        normalized.get("book_title"),
+        normalized.get("name"),
+        normalized.get("album"),
+        filename,
+    )
+    authors = split_people_field(
+        normalized.get("authors")
+        or normalized.get("author")
+        or normalized.get("album_artist")
+        or normalized.get("artist")
+    )
+    narrators = split_people_field(normalized.get("narrators") or normalized.get("narrator"))
+    description = first_nonempty(
+        normalized.get("description"), normalized.get("summary"), normalized.get("comment")
+    )
+    genres = split_simple_list(normalized.get("genre"))
+    keywords = split_simple_list(normalized.get("tags") or normalized.get("keywords"))
+    lang = first_nonempty(normalized.get("language"), normalized.get("lang")) or language or ""
+    series_name = first_nonempty(
+        normalized.get("series"),
+        normalized.get("series_name"),
+        normalized.get("seriesname"),
+        normalized.get("series_title"),
+        normalized.get("seriestitle"),
+    )
+
+    series_sequence = None
+    for key in _SERIES_SEQUENCE_TAG_KEYS:
+        raw_value = normalized.get(key)
+        seq = normalize_series_sequence(raw_value)
+        if seq:
+            series_sequence = seq
+            break
+    if not series_name:
+        series_sequence = None
+
+    data: Dict[str, Any] = {
+        "title": title,
+        "subtitle": normalized.get("subtitle"),
+        "authors": authors,
+        "narrators": narrators,
+        "description": description,
+        "publisher": normalized.get("publisher"),
+        "genres": genres,
+        "tags": keywords,
+        "language": lang,
+        "publishedYear": extract_year(
+            normalized.get("published")
+            or normalized.get("publication_year")
+            or normalized.get("date")
+            or normalized.get("year")
+        ),
+        "seriesName": series_name,
+        "seriesSequence": series_sequence,
+        "isbn": first_nonempty(normalized.get("isbn"), normalized.get("asin")),
+    }
+    published_date = first_nonempty(
+        normalized.get("published"), normalized.get("publication_date"), normalized.get("date")
+    )
+    if published_date:
+        data["publishedDate"] = published_date
+
+    rating_text = first_nonempty(normalized.get("rating"), normalized.get("my_rating"))
+    if rating_text:
+        try:
+            data["rating"] = float(str(rating_text).strip())
+        except ValueError:
+            pass
+        rating_max_text = first_nonempty(
+            normalized.get("rating_max"), normalized.get("rating_scale")
+        )
+        if rating_max_text:
+            try:
+                data["ratingMax"] = float(str(rating_max_text).strip())
+            except ValueError:
+                pass
+
+    cleaned: Dict[str, Any] = {}
+    for key, value in data.items():
+        if value is None:
+            continue
+        if isinstance(value, str) and not value.strip():
+            continue
+        if isinstance(value, (list, tuple)) and not value:
+            continue
+        cleaned[key] = value
+    return cleaned
+
+
+def load_audiobookshelf_chapters(
+    metadata_path: Path,
+) -> Optional[List[Dict[str, Any]]]:
+    if not metadata_path.exists():
+        return None
+    try:
+        payload = json.loads(metadata_path.read_text(encoding="utf-8"))
+    except (OSError, json.JSONDecodeError):
+        return None
+    chapters = payload.get("chapters")
+    if not isinstance(chapters, list):
+        return None
+    cleaned: List[Dict[str, Any]] = []
+    for entry in chapters:
+        if not isinstance(entry, Mapping):
+            continue
+        title = first_nonempty(entry.get("title"), entry.get("original_title"))
+        start = entry.get("start")
+        end = entry.get("end")
+        if title and start is not None and end is not None:
+            cleaned.append({"title": str(title), "start": start, "end": end})
+    return cleaned or None

abogen/domain/metadata_merge.py

@@ -0,0 +1,23 @@
+from __future__ import annotations
+
+from typing import Any, Dict, Optional
+
+
+def merge_metadata(
+    extracted: Optional[Dict[str, Any]],
+    overrides: Optional[Dict[str, Any]],
+) -> Dict[str, str]:
+    merged: Dict[str, str] = {}
+    if extracted:
+        for key, value in extracted.items():
+            if value is None:
+                continue
+            merged[str(key)] = str(value)
+    if overrides:
+        for key, value in overrides.items():
+            key_str = str(key)
+            if value is None:
+                merged.pop(key_str, None)
+            else:
+                merged[key_str] = str(value)
+    return merged

abogen/domain/metadata_overrides.py

@@ -0,0 +1,99 @@
+"""OPDS metadata normalization.
+
+Normalizes metadata keys from various OPDS/Calibre sources into
+a canonical set of overrides for the audiobook conversion pipeline.
+"""
+
+from __future__ import annotations
+
+from typing import Any, Dict, Mapping
+
+
+def normalize_opds_metadata(metadata_payload: Mapping[str, Any]) -> Dict[str, Any]:
+    """Normalize OPDS/Calibre metadata into canonical override keys.
+
+    Takes a metadata payload with various key aliases (e.g. 'series'/'series_name',
+    'tags'/'keywords', 'authors'/'creator') and returns a dict with canonical
+    keys set.
+
+    Args:
+        metadata_payload: Raw metadata dict from OPDS/Calibre import.
+
+    Returns:
+        Dict with canonical metadata keys (series, series_index, tags,
+        description, subtitle, publisher, authors).
+    """
+    metadata_overrides: Dict[str, Any] = {}
+
+    def _stringify(value: Any) -> str:
+        if value is None:
+            return ""
+        if isinstance(value, (list, tuple, set)):
+            parts = [str(item).strip() for item in value if item is not None]
+            return ", ".join(part for part in parts if part)
+        return str(value).strip()
+
+    raw_series = metadata_payload.get("series") or metadata_payload.get("series_name")
+    series_name = str(raw_series or "").strip()
+    if series_name:
+        metadata_overrides["series"] = series_name
+        metadata_overrides.setdefault("series_name", series_name)
+
+    series_index_value = (
+        metadata_payload.get("series_index")
+        or metadata_payload.get("series_position")
+        or metadata_payload.get("series_sequence")
+        or metadata_payload.get("book_number")
+    )
+    if series_index_value is not None:
+        series_index_text = str(series_index_value).strip()
+        if series_index_text:
+            metadata_overrides.setdefault("series_index", series_index_text)
+            metadata_overrides.setdefault("series_position", series_index_text)
+            metadata_overrides.setdefault("series_sequence", series_index_text)
+            metadata_overrides.setdefault("book_number", series_index_text)
+
+    tags_value = metadata_payload.get("tags") or metadata_payload.get("keywords")
+    if tags_value:
+        tags_text = _stringify(tags_value)
+        if tags_text:
+            metadata_overrides.setdefault("tags", tags_text)
+            metadata_overrides.setdefault("keywords", tags_text)
+            metadata_overrides.setdefault("genre", tags_text)
+
+    description_value = metadata_payload.get("description") or metadata_payload.get("summary")
+    if description_value:
+        description_text = _stringify(description_value)
+        if description_text:
+            metadata_overrides.setdefault("description", description_text)
+            metadata_overrides.setdefault("summary", description_text)
+
+    subtitle_value = (
+        metadata_payload.get("subtitle")
+        or metadata_payload.get("sub_title")
+        or metadata_payload.get("calibre_subtitle")
+    )
+    if subtitle_value:
+        subtitle_text = _stringify(subtitle_value)
+        if subtitle_text:
+            metadata_overrides.setdefault("subtitle", subtitle_text)
+
+    publisher_value = metadata_payload.get("publisher")
+    if publisher_value:
+        publisher_text = _stringify(publisher_value)
+        if publisher_text:
+            metadata_overrides.setdefault("publisher", publisher_text)
+
+    authors_value = (
+        metadata_payload.get("authors")
+        or metadata_payload.get("author")
+        or metadata_payload.get("creator")
+        or metadata_payload.get("dc_creator")
+    )
+    if authors_value:
+        authors_text = _stringify(authors_value)
+        if authors_text:
+            metadata_overrides.setdefault("authors", authors_text)
+            metadata_overrides.setdefault("author", authors_text)
+
+    return metadata_overrides

abogen/domain/normalization.py

@@ -0,0 +1,125 @@
+"""Text normalization convenience helpers.
+
+Provides both the simple ``normalize_text_for_pipeline`` (apostrophe + LLM only)
+and the comprehensive ``prepare_text_for_tts`` that chains all three normalization
+stages used during conversion: heteronym rules → pronunciation rules → pipeline
+normalization.  The latter is the single entry point that both the Web UI and
+PyQt Desktop GUI should use.
+
+Also provides ``TTSContext`` — a dataclass bundling all pre-compiled normalization
+resources so they can be created once and passed as a single object.
+"""
+
+from __future__ import annotations
+
+from dataclasses import dataclass, field
+from typing import Any, Dict, List, Mapping, Optional
+
+from abogen.kokoro_text_normalization import (
+    ApostropheConfig,
+    normalize_for_pipeline as _normalize_for_pipeline,
+)
+from abogen.normalization_settings import (
+    build_apostrophe_config,
+    get_runtime_settings,
+    apply_overrides as _apply_overrides,
+)
+
+_BASE_APOSTROPHE_CONFIG = ApostropheConfig()
+
+
+@dataclass
+class TTSContext:
+    """Bundles pre-compiled normalization resources for TTS processing.
+
+    Created once per conversion job and passed to ``prepare_text_for_tts``
+    instead of threading 5 separate parameters.
+    """
+
+    split_pattern: str = r"(?<=[.!?\-])\s+"
+    pronunciation_rules: Optional[List[Dict[str, Any]]] = None
+    heteronym_rules: Optional[List[Dict[str, Any]]] = None
+    normalization_overrides: Optional[Mapping[str, Any]] = None
+    usage_counter: Dict[str, int] = field(default_factory=dict)
+
+    def normalize(self, text: str) -> str:
+        """Shorthand: normalize text using this context's compiled rules."""
+        return prepare_text_for_tts(
+            text,
+            heteronym_rules=self.heteronym_rules,
+            pronunciation_rules=self.pronunciation_rules,
+            normalization_overrides=self.normalization_overrides,
+            usage_counter=self.usage_counter,
+        )
+
+
+def normalize_text_for_pipeline(
+    text: str,
+    *,
+    normalization_overrides: Optional[Mapping[str, Any]] = None,
+) -> str:
+    """Normalize text using runtime settings with optional overrides."""
+    runtime_settings = get_runtime_settings()
+    if normalization_overrides:
+        runtime_settings = _apply_overrides(runtime_settings, normalization_overrides)
+    apostrophe_config = build_apostrophe_config(settings=runtime_settings, base=_BASE_APOSTROPHE_CONFIG)
+    return _normalize_for_pipeline(text, config=apostrophe_config, settings=runtime_settings)
+
+
+def prepare_text_for_tts(
+    text: str,
+    *,
+    heteronym_rules: Optional[List[Dict[str, Any]]] = None,
+    pronunciation_rules: Optional[List[Dict[str, Any]]] = None,
+    normalization_overrides: Optional[Mapping[str, Any]] = None,
+    usage_counter: Optional[Dict[str, int]] = None,
+) -> str:
+    """Apply the full text normalization pipeline before TTS synthesis.
+
+    Chains three stages in order:
+      1. Heteronym sentence rules (context-dependent pronunciation)
+      2. Pronunciation rules (token-level replacements)
+      3. Pipeline normalization (apostrophe handling, LLM normalization)
+
+    This is the **single entry point** that both the Web UI conversion runner
+    and the PyQt conversion thread should call before passing text to the TTS
+    backend.
+
+    Parameters
+    ----------
+    text:
+        Raw text to normalize.
+    heteronym_rules:
+        Compiled heteronym rules from ``compile_heteronym_sentence_rules``.
+    pronunciation_rules:
+        Compiled pronunciation rules from ``compile_pronunciation_rules``.
+    normalization_overrides:
+        User-level overrides for normalization settings (apostrophe mode, etc.).
+    usage_counter:
+        Mutable dict that tracks how many times each pronunciation override was
+        applied.  Passed through to ``apply_pronunciation_rules``.
+
+    Returns
+    -------
+    str
+        Fully normalized text ready for TTS.
+    """
+    from abogen.domain.pronunciation import (
+        apply_heteronym_sentence_rules,
+        apply_pronunciation_rules,
+    )
+
+    result = str(text or "")
+
+    if heteronym_rules:
+        result = apply_heteronym_sentence_rules(result, heteronym_rules)
+
+    if pronunciation_rules:
+        result = apply_pronunciation_rules(result, pronunciation_rules, usage_counter)
+
+    runtime_settings = get_runtime_settings()
+    if normalization_overrides:
+        runtime_settings = _apply_overrides(runtime_settings, normalization_overrides)
+    apostrophe_config = build_apostrophe_config(settings=runtime_settings, base=_BASE_APOSTROPHE_CONFIG)
+
+    return _normalize_for_pipeline(result, config=apostrophe_config, settings=runtime_settings)

abogen/domain/output_paths.py

@@ -0,0 +1,180 @@
+"""Output path resolution utilities.
+
+Pure functions for resolving output directories, building file paths,
+and computing project folder layouts.
+"""
+
+from __future__ import annotations
+
+import os
+import platform
+import re
+from datetime import datetime
+from pathlib import Path
+from typing import Any, Callable, List, Optional, Tuple
+
+from abogen.subtitle_utils import sanitize_name_for_os
+from abogen.text_extractor import ExtractedChapter
+
+
+_OUTPUT_SANITIZE_RE = re.compile(r"[^\w\-_.]+")
+
+# OS-specific illegal characters for filenames
+_WINDOWS_ILLEGAL_CHARS_RE = re.compile(r'[<>:"/\\|?*\x00-\x1f]')
+_UNIX_CONTROL_CHARS_RE = re.compile(r'[\x00-\x1f]')
+_RESERVED_NAMES = frozenset(
+    {"CON", "PRN", "AUX", "NUL"}
+    | {f"COM{i}" for i in range(1, 10)}
+    | {f"LPT{i}" for i in range(1, 10)}
+)
+
+
+def slugify(title: str, index: int) -> str:
+    sanitized = re.sub(r"[^\w\-]+", "_", title.lower()).strip("_")
+    if not sanitized:
+        sanitized = f"chapter_{index:02d}"
+    return sanitized[:80]
+
+
+def sanitize_filename_for_chapter(title: str, index: int, max_len: int = 80) -> str:
+    """Sanitize a chapter name for use as a filename component.
+
+    Combines character sanitization, OS safety, and smart truncation
+    at word boundaries. Prepends zero-padded index prefix.
+
+    Args:
+        title: Raw chapter title.
+        index: 1-based chapter number for prefix.
+        max_len: Maximum length of the sanitized portion (excluding prefix).
+
+    Returns:
+        Sanitized string like "01_the_beginning".
+    """
+    # Remove non-word/non-space/non-hyphen chars, then collapse spaces/hyphens
+    sanitized = re.sub(r"[^\w\s\-]", "", title)
+    sanitized = re.sub(r"[\s\-]+", "_", sanitized).strip("_")
+
+    if not sanitized:
+        sanitized = f"chapter_{index:02d}"
+
+    # OS-specific sanitization
+    system = platform.system()
+    if system == "Windows":
+        sanitized = _WINDOWS_ILLEGAL_CHARS_RE.sub("_", sanitized)
+        sanitized = sanitized.rstrip(". ")
+        base = sanitized.split(".")[0].upper()
+        if base in _RESERVED_NAMES:
+            sanitized = f"_{sanitized}"
+    # Linux: only NUL is truly illegal, but control chars are problematic
+    sanitized = _UNIX_CONTROL_CHARS_RE.sub("_", sanitized)
+
+    # Smart truncation at word boundary
+    if len(sanitized) > max_len:
+        pos = sanitized[:max_len].rfind("_")
+        sanitized = sanitized[: pos if pos > 0 else max_len].rstrip("_")
+
+    return f"{index:02d}_{sanitized}"
+
+
+def sanitize_output_stem(name: str) -> str:
+    base = Path(name or "").stem
+    sanitized = _OUTPUT_SANITIZE_RE.sub("_", base).strip("_")
+    return sanitized or "output"
+
+
+def output_timestamp_token() -> str:
+    return datetime.now().strftime("%Y%m%d-%H%M%S")
+
+
+def build_output_path(directory: Path, original_name: str, extension: str) -> Path:
+    sanitized = sanitize_output_stem(original_name)
+    return directory / f"{sanitized}.{extension}"
+
+
+def apply_newline_policy(chapters: List[ExtractedChapter], replace_single_newlines: bool) -> None:
+    if not replace_single_newlines:
+        return
+    newline_regex = re.compile(r"(?<!\n)\n(?!\n)")
+    for chapter in chapters:
+        chapter.text = newline_regex.sub(" ", chapter.text)
+
+
+def resolve_output_directory(
+    *,
+    save_mode: str,
+    stored_path: Path,
+    output_folder: Optional[str],
+    desktop_dir: Optional[Path],
+    user_output_path: Optional[Path],
+    user_cache_outputs: Optional[Path],
+) -> Path:
+    if save_mode == "Save to Desktop" and desktop_dir:
+        return desktop_dir
+    if save_mode == "Save next to input file":
+        return stored_path.parent
+    if save_mode == "Choose output folder" and output_folder:
+        return Path(output_folder)
+    if save_mode == "Use default save location" and user_output_path:
+        return user_output_path
+    return user_cache_outputs or Path(".")
+
+
+def resolve_project_layout(
+    *,
+    original_filename: str,
+    save_as_project: bool,
+    base_dir: Path,
+    timestamp_fn: Callable[[], str] = output_timestamp_token,
+    sanitize_fn: Callable[[str, int], str] = sanitize_output_stem,
+) -> Tuple[Path, Path, Path, Optional[Path]]:
+    sanitized = sanitize_fn(original_filename, 0)
+    folder_name = f"{timestamp_fn()}_{sanitized}"
+    project_root = base_dir / folder_name
+    project_root.mkdir(parents=True, exist_ok=True)
+
+    if save_as_project:
+        audio_dir = project_root / "audio"
+        subtitle_dir = project_root / "subtitles"
+        metadata_dir = project_root / "metadata"
+        for directory in (audio_dir, subtitle_dir, metadata_dir):
+            directory.mkdir(parents=True, exist_ok=True)
+        return project_root, audio_dir, subtitle_dir, metadata_dir
+
+    return project_root, project_root, project_root, None
+
+
+def resolve_unique_path(
+    parent_dir: str,
+    base_name: str,
+    extension: str,
+    allowed_extensions: Optional[set] = None,
+) -> str:
+    """Find a unique file path by appending _2, _3, etc. on collision.
+
+    Args:
+        parent_dir: Directory to check for collisions.
+        base_name: Base filename (without extension).
+        extension: File extension (without dot).
+        allowed_extensions: Set of extensions to check against.
+            If None, checks any existing file/dir with same name.
+
+    Returns:
+        Full path without extension (e.g. "/path/to/name_2").
+    """
+    sanitized = sanitize_name_for_os(base_name, is_folder=True)
+    counter = 1
+    while True:
+        suffix = f"_{counter}" if counter > 1 else ""
+        candidate = os.path.join(parent_dir, f"{sanitized}{suffix}")
+        if allowed_extensions is not None:
+            file_parts = (os.path.splitext(f) for f in os.listdir(parent_dir))
+            clash = any(
+                name == f"{sanitized}{suffix}"
+                and ext[1:].lower() in allowed_extensions
+                for name, ext in file_parts
+            )
+        else:
+            clash = os.path.exists(candidate)
+        if not clash:
+            return candidate
+        counter += 1

abogen/domain/pipeline_factory.py

@@ -0,0 +1,107 @@
+"""Pipeline creation, caching and lifecycle management.
+
+Provides a unified interface for creating and managing TTS pipelines
+across all UI layers (WebUI, PyQt, CLI).
+"""
+
+from __future__ import annotations
+
+from typing import Any, Dict, Optional
+
+from abogen.domain.device import select_device
+from abogen.domain.voice_resolution import initialize_voice_cache
+from abogen.tts_plugin.utils import create_pipeline, is_plugin_registered
+
+
+def resolve_device(use_gpu: bool) -> str:
+    """Determine compute device from job and global config flags."""
+    from abogen.utils import load_config
+
+    cfg = load_config()
+    if use_gpu and cfg.get("use_gpu", True):
+        return select_device()
+    return "cpu"
+
+
+def create_pipeline_for_job(
+    provider: str,
+    language: str,
+    use_gpu: bool,
+) -> Any:
+    """Create a TTS pipeline with proper device selection.
+
+    Handles provider validation, GPU decision, and plugin checks.
+    """
+    provider = str(provider or "kokoro").strip().lower() or "kokoro"
+    if not is_plugin_registered(provider):
+        provider = "kokoro"
+
+    if provider == "supertonic":
+        return create_pipeline("supertonic")
+
+    device = resolve_device(use_gpu)
+    return create_pipeline("kokoro", lang_code=language, device=device)
+
+
+def dispose_pipelines(pipelines: Dict[str, Any]) -> None:
+    """Dispose all pipelines in a dict and clear it."""
+    for p in pipelines.values():
+        try:
+            p.dispose()
+        except Exception:
+            pass
+    pipelines.clear()
+
+
+class PipelinePool:
+    """Cache and manage TTS pipelines by provider.
+
+    Usage::
+
+        pool = PipelinePool()
+        backend = pool.get("kokoro", "en", use_gpu=True)
+        # ... use backend ...
+        pool.dispose_all()
+    """
+
+    def __init__(self) -> None:
+        self._pipelines: Dict[str, Any] = {}
+        self._voice_cache_initialized = False
+
+    def get(
+        self,
+        provider: str,
+        language: str,
+        use_gpu: bool,
+        *,
+        job: Any = None,
+    ) -> Any:
+        """Get or create a cached pipeline for the given provider.
+
+        Args:
+            provider: TTS provider name ("kokoro" or "supertonic").
+            language: Language code (for kokoro).
+            use_gpu: Whether GPU acceleration is requested.
+            job: Optional job object for voice cache initialization.
+        """
+        provider = str(provider or "kokoro").strip().lower() or "kokoro"
+        if not is_plugin_registered(provider):
+            provider = "kokoro"
+
+        existing = self._pipelines.get(provider)
+        if existing is not None:
+            return existing
+
+        pipeline = create_pipeline_for_job(provider, language, use_gpu)
+        self._pipelines[provider] = pipeline
+
+        if provider == "kokoro" and not self._voice_cache_initialized and job is not None:
+            initialize_voice_cache(job)
+            self._voice_cache_initialized = True
+
+        return pipeline
+
+    def dispose_all(self) -> None:
+        """Dispose all cached pipelines."""
+        dispose_pipelines(self._pipelines)
+        self._voice_cache_initialized = False

abogen/domain/progress.py

@@ -0,0 +1,72 @@
+from __future__ import annotations
+
+"""Progress and ETR (estimated time remaining) calculation.
+
+Shared by Web UI and PyQt desktop GUI. Pure math, no UI dependencies.
+"""
+import time
+from dataclasses import dataclass, field
+
+
+@dataclass
+class ProgressTracker:
+    """Tracks character-based progress with ETR calculation.
+
+    Usage:
+        tracker = ProgressTracker(total_chars=50000)
+        # ... as processing occurs:
+        tracker.update(chars_done=5000)
+        print(tracker.etr_str)   # "00:04:30"
+        print(tracker.percent)   # 10
+    """
+    total_chars: int
+    _start_time: float = field(default_factory=time.time, repr=False)
+    _chars_done: int = field(default=0, repr=False)
+
+    def update(self, chars_done: int) -> None:
+        self._chars_done = chars_done
+
+    @property
+    def percent(self) -> int:
+        if self.total_chars <= 0:
+            return 0
+        return min(int(self._chars_done / self.total_chars * 100), 99)
+
+    @property
+    def etr_str(self) -> str:
+        elapsed = time.time() - self._start_time
+        if self._chars_done <= 0 or elapsed <= 0.5:
+            return "Processing..."
+        avg_time_per_char = elapsed / self._chars_done
+        remaining = self.total_chars - self._chars_done
+        if remaining <= 0:
+            return "00:00:00"
+        secs = avg_time_per_char * remaining
+        h = int(secs // 3600)
+        m = int((secs % 3600) // 60)
+        s = int(secs % 60)
+        return f"{h:02d}:{m:02d}:{s:02d}"
+
+
+def calc_etr_str(elapsed: float, done: int, total: int) -> str:
+    """Standalone ETR string calculation (matches PyQt original logic).
+
+    Args:
+        elapsed: seconds since processing started
+        done: items/characters processed so far
+        total: total items/characters to process
+
+    Returns:
+        ETR string like "01:23:45" or "Processing..."
+    """
+    if done <= 0 or elapsed <= 0.5:
+        return "Processing..."
+    avg_time_per_item = elapsed / done
+    remaining = total - done
+    if remaining <= 0:
+        return "00:00:00"
+    secs = avg_time_per_item * remaining
+    h = int(secs // 3600)
+    m = int((secs % 3600) // 60)
+    s = int(secs % 60)
+    return f"{h:02d}:{m:02d}:{s:02d}"

abogen/domain/pronunciation.py

@@ -0,0 +1,261 @@
+"""Pronunciation rule compilation and application.
+
+Pure functions for compiling token-level and sentence-level pronunciation
+overrides into regex patterns, applying them to text, and merging multiple
+override sources with precedence rules.
+"""
+
+from __future__ import annotations
+
+import re
+from typing import Any, Dict, Iterable, List, Mapping, Optional
+
+from abogen.entity_analysis import normalize_token as normalize_entity_token
+from abogen.entity_analysis import normalize_manual_override_token
+
+
+def compile_pronunciation_rules(
+    overrides: Optional[Iterable[Mapping[str, Any]]],
+) -> List[Dict[str, Any]]:
+    if not overrides:
+        return []
+
+    candidates: List[Dict[str, Any]] = []
+    seen: set[str] = set()
+
+    for entry in overrides:
+        if not isinstance(entry, Mapping):
+            continue
+        pronunciation_value = str(entry.get("pronunciation") or "").strip()
+        if not pronunciation_value:
+            continue
+
+        token_values: List[str] = []
+        token_raw = entry.get("token")
+        if token_raw:
+            token_value = str(token_raw).strip()
+            if token_value:
+                token_values.append(token_value)
+        normalized_raw = entry.get("normalized")
+        if normalized_raw:
+            normalized_value = str(normalized_raw).strip()
+            if normalized_value:
+                token_values.append(normalized_value)
+        if token_raw and not token_values:
+            fallback = normalize_entity_token(str(token_raw))
+            if fallback:
+                token_values.append(fallback)
+
+        if not token_values:
+            continue
+
+        usage_normalized = str(entry.get("normalized") or "").strip()
+        if not usage_normalized and token_values:
+            usage_normalized = normalize_entity_token(token_values[0]) or token_values[0]
+        usage_token = str(entry.get("token") or token_values[0])
+
+        for token_value in token_values:
+            key = token_value.casefold()
+            if key in seen:
+                continue
+            seen.add(key)
+            candidates.append(
+                {
+                    "token": token_value,
+                    "normalized": usage_normalized,
+                    "replacement": pronunciation_value,
+                }
+            )
+
+    if not candidates:
+        return []
+
+    candidates.sort(key=lambda item: len(item["token"]), reverse=True)
+    compiled: List[Dict[str, Any]] = []
+    for candidate in candidates:
+        token_value = candidate["token"]
+        pronunciation_value = candidate["replacement"]
+        escaped = re.escape(token_value)
+        pattern = re.compile(rf"(?i)(?<!\w){escaped}(?P<possessive>'s|\u2019s|\u2019)?(?!\w)")
+        compiled.append(
+            {
+                "pattern": pattern,
+                "replacement": pronunciation_value,
+                "normalized": candidate.get("normalized") or token_value,
+                "token": candidate.get("token") or token_value,
+            }
+        )
+
+    return compiled
+
+
+def compile_heteronym_sentence_rules(
+    overrides: Optional[Iterable[Mapping[str, Any]]],
+) -> List[Dict[str, Any]]:
+    if not overrides:
+        return []
+
+    compiled: List[Dict[str, Any]] = []
+    seen: set[str] = set()
+
+    for entry in overrides:
+        if not isinstance(entry, Mapping):
+            continue
+        sentence = str(entry.get("sentence") or "").strip()
+        if not sentence:
+            continue
+        choice = str(entry.get("choice") or "").strip()
+        if not choice:
+            continue
+
+        replacement_sentence = ""
+        options = entry.get("options")
+        if isinstance(options, list):
+            for opt in options:
+                if not isinstance(opt, Mapping):
+                    continue
+                if str(opt.get("key") or "").strip() == choice:
+                    replacement_sentence = str(opt.get("replacement_sentence") or "").strip()
+                    break
+        if not replacement_sentence:
+            continue
+
+        rule_key = f"{sentence}\n{choice}".casefold()
+        if rule_key in seen:
+            continue
+        seen.add(rule_key)
+
+        parts = [p for p in re.split(r"\s+", sentence) if p]
+        if not parts:
+            continue
+        pattern_text = r"\s+".join(re.escape(p) for p in parts)
+        pattern = re.compile(pattern_text)
+        compiled.append({"pattern": pattern, "replacement": replacement_sentence})
+
+    compiled.sort(key=lambda item: len(item["pattern"].pattern), reverse=True)
+    return compiled
+
+
+def apply_heteronym_sentence_rules(text: str, rules: List[Dict[str, Any]]) -> str:
+    if not text or not rules:
+        return text
+    result = text
+    for rule in rules:
+        pattern = rule["pattern"]
+        replacement = rule["replacement"]
+        result = pattern.sub(replacement, result)
+    return result
+
+
+def apply_pronunciation_rules(
+    text: str,
+    rules: List[Dict[str, Any]],
+    usage_counter: Optional[Dict[str, int]] = None,
+) -> str:
+    if not text or not rules:
+        return text
+
+    result = text
+    for rule in rules:
+        pattern = rule["pattern"]
+        pronunciation_value = rule["replacement"]
+        usage_key = str(rule.get("normalized") or "").strip()
+
+        def _replacement(match: re.Match[str]) -> str:
+            suffix = match.group("possessive") or ""
+            if usage_counter is not None and usage_key:
+                usage_counter[usage_key] = usage_counter.get(usage_key, 0) + 1
+            return pronunciation_value + suffix
+
+        result = pattern.sub(_replacement, result)
+
+    return result
+
+
+def merge_pronunciation_overrides(job: Any) -> List[Dict[str, Any]]:
+    """Return pronunciation override entries, ensuring manual overrides are included.
+
+    Pending jobs keep both ``manual_overrides`` and ``pronunciation_overrides``, but the
+    latter can be stale if the UI didn't resync before enqueue. During conversion,
+    we must merge manual overrides so they always apply (before TTS).
+
+    Precedence: manual overrides win over existing entries for the same normalized key.
+    """
+
+    collected: Dict[str, Dict[str, Any]] = {}
+
+    existing = getattr(job, "pronunciation_overrides", None)
+    if isinstance(existing, list):
+        for entry in existing:
+            if not isinstance(entry, Mapping):
+                continue
+            token_value = str(entry.get("token") or "").strip()
+            pronunciation_value = str(entry.get("pronunciation") or "").strip()
+            if not token_value or not pronunciation_value:
+                continue
+            normalized = str(entry.get("normalized") or "").strip() or normalize_entity_token(token_value)
+            if not normalized:
+                continue
+            collected[normalized] = {
+                "token": token_value,
+                "normalized": normalized,
+                "pronunciation": pronunciation_value,
+                "voice": str(entry.get("voice") or "").strip() or None,
+                "notes": str(entry.get("notes") or "").strip() or None,
+                "context": str(entry.get("context") or "").strip() or None,
+                "source": str(entry.get("source") or "pronunciation"),
+                "language": getattr(job, "language", None),
+            }
+
+    speakers = getattr(job, "speakers", None)
+    if isinstance(speakers, dict):
+        for payload in speakers.values():
+            if not isinstance(payload, Mapping):
+                continue
+            token_value = str(payload.get("token") or "").strip()
+            pronunciation_value = str(payload.get("pronunciation") or "").strip()
+            if not token_value or not pronunciation_value:
+                continue
+            normalized = normalize_entity_token(token_value)
+            if not normalized:
+                continue
+            collected[normalized] = {
+                "token": token_value,
+                "normalized": normalized,
+                "pronunciation": pronunciation_value,
+                "voice": str(
+                    payload.get("resolved_voice")
+                    or payload.get("voice")
+                    or getattr(job, "voice", "")
+                ).strip()
+                or None,
+                "notes": None,
+                "context": None,
+                "source": "speaker",
+                "language": getattr(job, "language", None),
+            }
+
+    manual = getattr(job, "manual_overrides", None)
+    if isinstance(manual, list):
+        for entry in manual:
+            if not isinstance(entry, Mapping):
+                continue
+            token_value = str(entry.get("token") or "").strip()
+            pronunciation_value = str(entry.get("pronunciation") or "").strip()
+            if not token_value or not pronunciation_value:
+                continue
+            normalized = str(entry.get("normalized") or "").strip() or normalize_manual_override_token(token_value)
+            if not normalized:
+                continue
+            collected[normalized] = {
+                "token": token_value,
+                "normalized": normalized,
+                "pronunciation": pronunciation_value,
+                "voice": str(entry.get("voice") or "").strip() or None,
+                "notes": str(entry.get("notes") or "").strip() or None,
+                "context": str(entry.get("context") or "").strip() or None,
+                "source": str(entry.get("source") or "manual"),
+                "language": getattr(job, "language", None),
+            }
+
+    return list(collected.values())

abogen/domain/settings_core.py

@@ -0,0 +1,580 @@
+"""Shared settings core.
+
+Defines the SETTINGS_REGISTRY — the single source of truth for all settings.
+Every setting has a key, type, default, validation rules, and UI scope.
+Both Web UI and Desktop GUI must reference this registry.
+"""
+
+from __future__ import annotations
+
+import os
+import re
+from dataclasses import dataclass, field
+from typing import Any, Callable, Dict, Mapping, Optional, Sequence
+
+from abogen.constants import (
+    LANGUAGE_DESCRIPTIONS,
+    SUBTITLE_FORMATS,
+    SUPPORTED_SOUND_FORMATS,
+)
+from abogen.tts_plugin.utils import get_default_voice
+from abogen.normalization_settings import (
+    DEFAULT_LLM_PROMPT,
+    environment_llm_defaults,
+)
+
+
+# ── Schema ───────────────────────────────────────────────────────────
+
+@dataclass(frozen=True)
+class Setting:
+    """Contract for a single setting.
+
+    Attributes:
+        key: Config dict key (e.g. "output_format").
+        type_: Python type (bool, int, float, str, list).
+        default: Default value or callable returning one.
+        min_value: Minimum for numeric types.
+        max_value: Maximum for numeric types.
+        valid_values: Allowed values for str types (None = any).
+        gui_only: True if only used by PyQt Desktop GUI.
+        web_only: True if only used by Web UI.
+        normalizer: Optional callable(value, default) -> normalized_value.
+        description: Human-readable explanation.
+    """
+    key: str
+    type_: type
+    default: Any
+    min_value: float | None = None
+    max_value: float | None = None
+    valid_values: tuple[Any, ...] | None = None
+    gui_only: bool = False
+    web_only: bool = False
+    normalizer: Callable | None = None
+    description: str = ""
+
+    def coerce(self, value: Any, fallback: Any | None = None) -> Any:
+        """Coerce value to the declared type, returning fallback on failure."""
+        fb = fallback if fallback is not None else self.default
+        if self.type_ is bool:
+            if isinstance(value, bool):
+                return value
+            if isinstance(value, str):
+                return value.lower() in {"true", "1", "yes", "on"}
+            if value is None:
+                return fb
+            return bool(value)
+        if self.type_ is int:
+            try:
+                v = int(value)
+            except (TypeError, ValueError):
+                return fb
+            if self.min_value is not None:
+                v = max(int(self.min_value), v)
+            if self.max_value is not None:
+                v = min(int(self.max_value), v)
+            return v
+        if self.type_ is float:
+            try:
+                v = float(value)
+            except (TypeError, ValueError):
+                return fb
+            if self.min_value is not None:
+                v = max(self.min_value, v)
+            if self.max_value is not None:
+                v = min(self.max_value, v)
+            return v
+        if self.type_ is str:
+            if isinstance(value, str):
+                v = value.strip()
+                if self.valid_values and v not in self.valid_values:
+                    return fb
+                return v
+            return fb
+        if self.type_ is list:
+            if isinstance(value, (list, tuple, set)):
+                return list(value)
+            return fb
+        return value
+
+
+# ── Normalizers (used by Setting.normalizer) ─────────────────────────
+
+def _norm_save_mode(value: Any, default: str) -> str:
+    if isinstance(value, str):
+        if value in SAVE_MODE_LABELS:
+            return value
+        if value in LEGACY_SAVE_MODE_MAP:
+            return LEGACY_SAVE_MODE_MAP[value]
+    return default
+
+
+def _norm_voice_spec(value: Any, default: str) -> str:
+    if isinstance(value, str):
+        text = value.strip()
+        if not text:
+            return default
+        spec, profile_name = split_profile_spec(text)
+        if profile_name:
+            return f"speaker:{profile_name}"
+        return spec
+    return default
+
+
+def _norm_speaker_spec(value: Any, default: str) -> str:
+    if isinstance(value, str):
+        text = value.strip()
+        if not text:
+            return ""
+        spec, profile_name = split_profile_spec(text)
+        if profile_name:
+            return f"speaker:{profile_name}"
+        return spec
+    return ""
+
+
+def _norm_language_list(value: Any, default: list) -> list:
+    if isinstance(value, (list, tuple, set)):
+        return [code for code in value if isinstance(code, str) and code in LANGUAGE_DESCRIPTIONS]
+    if isinstance(value, str):
+        parts = [item.strip().lower() for item in value.split(",") if item.strip()]
+        return [code for code in parts if code in LANGUAGE_DESCRIPTIONS]
+    return default
+
+
+def _norm_stripped_str(value: Any, default: str) -> str:
+    return str(value or "").strip()
+
+
+def _norm_prompt(value: Any, default: str) -> str:
+    candidate = str(value or "").strip()
+    return candidate if candidate else default
+
+
+# ── Registry ─────────────────────────────────────────────────────────
+
+def _default_output_format() -> str:
+    return "wav"
+
+
+def _default_save_mode() -> str:
+    return "default_output" if has_output_override() else "save_next_to_input"
+
+
+def _default_llm(key: str) -> str:
+    return environment_llm_defaults().get(key, "")
+
+
+SETTINGS_REGISTRY: list[Setting] = [
+    # ── Core output ──────────────────────────────────────────────
+    Setting("output_format", str, "wav",
+            valid_values=tuple(SUPPORTED_SOUND_FORMATS),
+            description="Audio output format"),
+    Setting("subtitle_format", str, "srt",
+            valid_values=tuple(item[0] for item in SUBTITLE_FORMATS),
+            description="Subtitle file format"),
+    Setting("save_mode", str, _default_save_mode,
+            normalizer=_norm_save_mode,
+            description="Where to save output files"),
+    Setting("separate_chapters_format", str, "wav",
+            valid_values=("wav", "flac", "mp3", "opus"),
+            description="Format for separately saved chapters"),
+    Setting("chunk_level", str, "paragraph",
+            valid_values=("paragraph", "sentence"),
+            description="Text chunking granularity"),
+
+    # ── Voice ────────────────────────────────────────────────────
+    Setting("default_speaker", str, "",
+            normalizer=_norm_speaker_spec,
+            description="Default speaker name"),
+    Setting("default_voice", str, lambda: get_default_voice("kokoro"),
+            normalizer=_norm_voice_spec,
+            description="Default TTS voice"),
+    Setting("speed", float, 1.0, min_value=0.5, max_value=3.0,
+            gui_only=True,
+            description="TTS speed multiplier"),
+    Setting("supertonic_total_steps", int, 5, min_value=2, max_value=15,
+            description="SuperTonic processing steps"),
+    Setting("supertonic_speed", float, 1.0, min_value=0.7, max_value=2.0,
+            description="SuperTonic speed"),
+
+    # ── Chapter handling ─────────────────────────────────────────
+    Setting("silence_between_chapters", float, 2.0, min_value=0.0,
+            description="Silence gap between chapters (seconds)"),
+    Setting("chapter_intro_delay", float, 0.5, min_value=0.0,
+            description="Delay after chapter heading (seconds)"),
+    Setting("read_title_intro", bool, False,
+            description="Read chapter title as intro"),
+    Setting("read_closing_outro", bool, True,
+            description="Read closing/outro text"),
+    Setting("normalize_chapter_opening_caps", bool, True,
+            description="Normalize chapter opening caps"),
+    Setting("auto_prefix_chapter_titles", bool, True,
+            description="Auto-prefix chapter titles"),
+    Setting("save_chapters_separately", bool, False,
+            description="Save each chapter as separate file"),
+    Setting("merge_chapters_at_end", bool, True,
+            description="Merge chapters into single file"),
+    Setting("save_as_project", bool, False,
+            description="Save as editable project"),
+    Setting("generate_epub3", bool, False,
+            description="Generate EPUB3 output"),
+
+    # ── GPU / performance ────────────────────────────────────────
+    Setting("use_gpu", bool, True,
+            description="Use GPU acceleration"),
+
+    # ── Text processing ──────────────────────────────────────────
+    Setting("replace_single_newlines", bool, False,
+            description="Replace single newlines with spaces"),
+    Setting("max_subtitle_words", int, 50, min_value=1, max_value=500,
+            description="Max words per subtitle"),
+    Setting("enable_entity_recognition", bool, True,
+            description="Enable entity recognition"),
+
+    # ── Speaker analysis ─────────────────────────────────────────
+    Setting("speaker_analysis_threshold", int, 3, min_value=1, max_value=25,
+            description="Speaker analysis threshold"),
+    Setting("speaker_pronunciation_sentence", str, "This is {{name}} speaking.",
+            description="Template for pronunciation samples"),
+    Setting("speaker_random_languages", list, [],
+            normalizer=_norm_language_list,
+            description="Languages for random speaker assignment"),
+
+    # ── LLM ──────────────────────────────────────────────────────
+    Setting("llm_base_url", str, lambda: _default_llm("llm_base_url"),
+            normalizer=_norm_stripped_str,
+            description="LLM API base URL"),
+    Setting("llm_api_key", str, lambda: _default_llm("llm_api_key"),
+            normalizer=_norm_stripped_str,
+            description="LLM API key"),
+    Setting("llm_model", str, lambda: _default_llm("llm_model"),
+            normalizer=_norm_stripped_str,
+            description="LLM model name"),
+    Setting("llm_timeout", float, lambda: _default_llm("llm_timeout") or 30.0,
+            min_value=1.0,
+            description="LLM request timeout"),
+    Setting("llm_prompt", str, lambda: _default_llm("llm_prompt") or DEFAULT_LLM_PROMPT,
+            normalizer=_norm_prompt,
+            description="LLM normalization prompt"),
+    Setting("llm_context_mode", str, lambda: _default_llm("llm_context_mode") or "sentence",
+            valid_values=("sentence",),
+            description="LLM context mode"),
+
+    # ── Normalization (booleans) ─────────────────────────────────
+    Setting("normalization_numbers", bool, True,
+            description="Convert grouped numbers to words"),
+    Setting("normalization_currency", bool, True,
+            description="Convert currency symbols"),
+    Setting("normalization_footnotes", bool, True,
+            description="Remove footnote indicators"),
+    Setting("normalization_titles", bool, True,
+            description="Expand titles and suffixes"),
+    Setting("normalization_terminal", bool, True,
+            description="Ensure terminal punctuation"),
+    Setting("normalization_phoneme_hints", bool, True,
+            description="Add phoneme hints for possessives"),
+    Setting("normalization_caps_quotes", bool, True,
+            description="Convert ALL CAPS in quotes"),
+    Setting("normalization_internet_slang", bool, False,
+            description="Expand internet slang"),
+    Setting("normalization_apostrophes_contractions", bool, True,
+            description="Expand contractions"),
+    Setting("normalization_apostrophes_plural_possessives", bool, True,
+            description="Collapse plural possessives"),
+    Setting("normalization_apostrophes_sibilant_possessives", bool, True,
+            description="Mark sibilant possessives"),
+    Setting("normalization_apostrophes_decades", bool, True,
+            description="Expand decades"),
+    Setting("normalization_apostrophes_leading_elisions", bool, True,
+            description="Expand leading elisions"),
+    Setting("normalization_contraction_aux_be", bool, True,
+            description="Expand auxiliary 'be'"),
+    Setting("normalization_contraction_aux_have", bool, True,
+            description="Expand auxiliary 'have'"),
+    Setting("normalization_contraction_modal_will", bool, True,
+            description="Expand modal 'will'"),
+    Setting("normalization_contraction_modal_would", bool, True,
+            description="Expand modal 'would'"),
+    Setting("normalization_contraction_negation_not", bool, True,
+            description="Expand negation 'not'"),
+    Setting("normalization_contraction_let_us", bool, True,
+            description="Expand 'let's'"),
+
+    # ── Normalization (strings) ──────────────────────────────────
+    Setting("normalization_apostrophe_mode", str, "spacy",
+            valid_values=("off", "spacy", "llm"),
+            description="Apostrophe handling mode"),
+    Setting("normalization_numbers_year_style", str, "american",
+            valid_values=("american", "off"),
+            description="Year style for number normalization"),
+
+    # ── PyQt GUI-only ────────────────────────────────────────────
+    Setting("theme", str, "system",
+            gui_only=True,
+            description="UI theme"),
+    Setting("check_updates", bool, True,
+            gui_only=True,
+            description="Check for updates on startup"),
+    Setting("subtitle_mode", str, "Sentence",
+            gui_only=True,
+            description="Subtitle display mode"),
+    Setting("selected_format", str, "wav",
+            gui_only=True,
+            description="Last selected audio format"),
+    Setting("selected_voice", str, "af_heart",
+            gui_only=True,
+            description="Last selected voice"),
+    Setting("selected_profile_name", str, None,
+            gui_only=True,
+            description="Last selected profile name"),
+    Setting("log_window_max_lines", int, 2000, min_value=100,
+            gui_only=True,
+            description="Max lines in log window"),
+    Setting("use_silent_gaps", bool, True,
+            gui_only=True,
+            description="Use silent gaps between chunks"),
+    Setting("subtitle_speed_method", str, "tts",
+            gui_only=True,
+            valid_values=("tts", "ffmpeg"),
+            description="Speed adjustment method for subtitles"),
+    Setting("use_spacy_segmentation", bool, True,
+            gui_only=True,
+            description="Use spaCy for sentence segmentation"),
+    Setting("word_substitutions_enabled", bool, False,
+            gui_only=True,
+            description="Enable word substitutions"),
+    Setting("word_substitutions_list", str, "",
+            gui_only=True,
+            description="Word substitutions list"),
+    Setting("case_sensitive_substitutions", bool, False,
+            gui_only=True,
+            description="Case-sensitive substitutions"),
+    Setting("replace_all_caps", bool, False,
+            gui_only=True,
+            description="Replace ALL CAPS text"),
+    Setting("replace_numerals", bool, False,
+            gui_only=True,
+            description="Replace numerals with words"),
+    Setting("fix_nonstandard_punctuation", bool, False,
+            gui_only=True,
+            description="Fix nonstandard punctuation"),
+    Setting("queue_override_settings", bool, False,
+            gui_only=True,
+            description="Override settings per queue item"),
+    Setting("disable_kokoro_internet", bool, False,
+            description="Disable Kokoro internet access"),
+]
+
+
+# ── Registry helpers ─────────────────────────────────────────────────
+
+_REGISTRY_BY_KEY: dict[str, Setting] = {s.key: s for s in SETTINGS_REGISTRY}
+
+SETTING_KEYS: frozenset[str] = frozenset(_REGISTRY_BY_KEY.keys())
+GUI_ONLY_KEYS: frozenset[str] = frozenset(s.key for s in SETTINGS_REGISTRY if s.gui_only)
+WEB_ONLY_KEYS: frozenset[str] = frozenset(s.key for s in SETTINGS_REGISTRY if s.web_only)
+SHARED_KEYS: frozenset[str] = SETTING_KEYS - GUI_ONLY_KEYS - WEB_ONLY_KEYS
+
+BOOLEAN_SETTINGS: frozenset[str] = frozenset(s.key for s in SETTINGS_REGISTRY if s.type_ is bool)
+FLOAT_SETTINGS: frozenset[str] = frozenset(s.key for s in SETTINGS_REGISTRY if s.type_ is float)
+INT_SETTINGS: frozenset[str] = frozenset(s.key for s in SETTINGS_REGISTRY if s.type_ is int)
+
+# Backward-compatible aliases (used by existing code)
+_NORMALIZATION_BOOLEAN_KEYS: frozenset[str] = frozenset(
+    s.key for s in SETTINGS_REGISTRY
+    if s.type_ is bool and s.key.startswith("normalization_")
+)
+_NORMALIZATION_STRING_KEYS: frozenset[str] = frozenset(
+    s.key for s in SETTINGS_REGISTRY
+    if s.type_ is str and s.key.startswith("normalization_")
+)
+
+
+def get_setting(key: str) -> Setting | None:
+    """Look up a setting by key."""
+    return _REGISTRY_BY_KEY.get(key)
+
+
+def has_output_override() -> bool:
+    return bool(os.environ.get("ABOGEN_OUTPUT_DIR") or os.environ.get("ABOGEN_OUTPUT_ROOT"))
+
+
+# ── Defaults ─────────────────────────────────────────────────────────
+
+def settings_defaults() -> Dict[str, Any]:
+    """Default values for all shared settings (excludes gui_only)."""
+    result: Dict[str, Any] = {}
+    for s in SETTINGS_REGISTRY:
+        if s.gui_only:
+            continue
+        result[s.key] = s.default() if callable(s.default) else s.default
+    return result
+
+
+def all_settings_defaults() -> Dict[str, Any]:
+    """Default values for ALL settings (including gui_only)."""
+    result: Dict[str, Any] = {}
+    for s in SETTINGS_REGISTRY:
+        result[s.key] = s.default() if callable(s.default) else s.default
+    return result
+
+
+def load_settings() -> Dict[str, Any]:
+    """Load and normalize settings from config file."""
+    from abogen.utils import load_config
+    defaults = settings_defaults()
+    cfg = load_config() or {}
+    settings: Dict[str, Any] = {}
+    for key, default in defaults.items():
+        raw_value = cfg.get(key, default)
+        settings[key] = normalize_setting_value(key, raw_value, defaults)
+    return settings
+
+
+# ── Normalization (delegates to Setting.coerce) ──────────────────────
+
+def normalize_setting_value(key: str, value: Any, defaults: Dict[str, Any]) -> Any:
+    """Normalize a single setting value using the registry schema."""
+    setting = _REGISTRY_BY_KEY.get(key)
+    if setting is None:
+        return value if value is not None else defaults.get(key)
+
+    fallback = defaults.get(key, setting.default() if callable(setting.default) else setting.default)
+
+    if setting.normalizer is not None:
+        return setting.normalizer(value, fallback)
+
+    return setting.coerce(value, fallback)
+
+
+def validate_setting(key: str, value: Any) -> tuple[bool, str]:
+    """Validate a setting value against its schema. Returns (ok, error_message)."""
+    setting = _REGISTRY_BY_KEY.get(key)
+    if setting is None:
+        return False, f"Unknown setting: {key}"
+    if setting.type_ is str and setting.valid_values is not None:
+        v = str(value or "").strip()
+        if v and v not in setting.valid_values:
+            return False, f"Invalid value '{v}' for {key}. Allowed: {setting.valid_values}"
+    if setting.type_ is int:
+        try:
+            iv = int(value)
+        except (TypeError, ValueError):
+            return False, f"Invalid integer value for {key}: {value!r}"
+        if setting.min_value is not None and iv < setting.min_value:
+            return False, f"{key} must be >= {setting.min_value}, got {iv}"
+        if setting.max_value is not None and iv > setting.max_value:
+            return False, f"{key} must be <= {setting.max_value}, got {iv}"
+    if setting.type_ is float:
+        try:
+            fv = float(value)
+        except (TypeError, ValueError):
+            return False, f"Invalid float value for {key}: {value!r}"
+        if setting.min_value is not None and fv < setting.min_value:
+            return False, f"{key} must be >= {setting.min_value}, got {fv}"
+        if setting.max_value is not None and fv > setting.max_value:
+            return False, f"{key} must be <= {setting.max_value}, got {fv}"
+    return True, ""
+
+
+# ── Constants (backward-compatible) ──────────────────────────────────
+
+SAVE_MODE_LABELS = {
+    "save_next_to_input": "Save next to input file",
+    "save_to_desktop": "Save to Desktop",
+    "choose_output_folder": "Choose output folder",
+    "default_output": "Use default save location",
+}
+
+LEGACY_SAVE_MODE_MAP = {label: key for key, label in SAVE_MODE_LABELS.items()}
+
+CHUNK_LEVEL_OPTIONS = [
+    {"value": "paragraph", "label": "Paragraphs"},
+    {"value": "sentence", "label": "Sentences"},
+]
+
+CHUNK_LEVEL_VALUES = frozenset(option["value"] for option in CHUNK_LEVEL_OPTIONS)
+
+DEFAULT_ANALYSIS_THRESHOLD = 3
+
+
+# ── Coercion helpers (backward-compatible, delegate to Setting.coerce) ──
+
+def coerce_bool(value: Any, default: bool) -> bool:
+    return Setting("_", bool, default).coerce(value, default)
+
+
+def coerce_float(value: Any, default: float) -> float:
+    return Setting("_", float, default).coerce(value, default)
+
+
+def coerce_int(value: Any, default: int, *, minimum: int = 1, maximum: int = 200) -> int:
+    return Setting("_", int, default, min_value=minimum, max_value=maximum).coerce(value, default)
+
+
+def split_profile_spec(value: Any) -> tuple[str, str | None]:
+    """Split 'speaker:Name' or 'profile:Name' into (raw, name)."""
+    text = str(value or "").strip()
+    if not text:
+        return "", None
+    lowered = text.lower()
+    if lowered.startswith("profile:") or lowered.startswith("speaker:"):
+        _, _, remainder = text.partition(":")
+        name = remainder.strip()
+        return "", name or None
+    return text, None
+
+
+def normalize_save_mode(value: Any, default: str) -> str:
+    return _norm_save_mode(value, default)
+
+
+# ── LLM helpers ──────────────────────────────────────────────────────
+
+_PROMPT_TOKEN_RE = re.compile(r"{{\s*([a-zA-Z0-9_]+)\s*}}")
+
+
+def llm_ready(settings: Mapping[str, Any]) -> bool:
+    base_url = str(settings.get("llm_base_url") or "").strip()
+    return bool(base_url)
+
+
+def render_prompt_template(template: str, context: Mapping[str, str]) -> str:
+    if not template:
+        return ""
+
+    def _replace(match: re.Match[str]) -> str:
+        key = match.group(1)
+        return context.get(key, "")
+
+    return _PROMPT_TOKEN_RE.sub(_replace, template)
+
+
+# ── Integration defaults ─────────────────────────────────────────────
+
+def integration_defaults() -> Dict[str, Dict[str, Any]]:
+    """Default values for integration settings."""
+    return {
+        "calibre_opds": {
+            "enabled": False,
+            "base_url": "",
+            "username": "",
+            "password": "",
+            "verify_ssl": True,
+        },
+        "audiobookshelf": {
+            "enabled": False,
+            "base_url": "",
+            "api_token": "",
+            "library_id": "",
+            "collection_id": "",
+            "folder_id": "",
+            "verify_ssl": True,
+            "send_cover": True,
+            "send_chapters": True,
+            "send_subtitles": False,
+            "auto_send": False,
+            "timeout": 30.0,
+        },
+    }

abogen/domain/split_pattern.py

@@ -0,0 +1,40 @@
+from __future__ import annotations
+
+"""Unified split pattern logic extracted from 3 copies."""
+import re
+
+
+PUNCTUATION_SENTENCE = r".!?。！？"
+PUNCTUATION_SENTENCE_COMMA = r".!?,。！？、，"
+
+
+def get_split_pattern(language: str, subtitle_mode: str) -> str:
+    """Get the appropriate split pattern based on language and subtitle mode.
+
+    Args:
+        language: Language code (a, b, e, f, etc.)
+        subtitle_mode: Subtitle mode ("Sentence", "Sentence + Comma", "Line", etc.)
+
+    Returns:
+        Split pattern string
+    """
+    # For English, always use newline splitting only
+    if language in ("a", "b"):
+        return "\n"
+
+    # Determine spacing pattern based on language
+    spacing = r"\s*" if language in ("z", "j") else r"\s+"
+
+    # For CJK languages, when subtitle mode is Disabled or Line, prefer
+    # punctuation-based splitting instead of plain newline splitting.
+    if subtitle_mode in ("Disabled", "Line") and language in ("z", "j"):
+        return rf"(?<=[{PUNCTUATION_SENTENCE}]){spacing}|\n+"
+
+    if subtitle_mode == "Line":
+        return "\n"
+    elif subtitle_mode == "Sentence":
+        return rf"(?<=[{PUNCTUATION_SENTENCE}]){spacing}|\n+"
+    elif subtitle_mode == "Sentence + Comma":
+        return rf"(?<=[{PUNCTUATION_SENTENCE_COMMA}]){spacing}|\n+"
+    else:
+        return r"\n+"

abogen/domain/subtitle_generation.py

@@ -0,0 +1,358 @@
+"""Subtitle generation utilities for audiobook generation.
+
+This module provides functions for processing TTS tokens into subtitle entries
+according to various subtitle modes (Line, Sentence, Sentence + Comma,
+Sentence + Highlighting).
+"""
+
+from __future__ import annotations
+
+import re
+from typing import List, Optional, Tuple
+
+
+# Punctuation constants for sentence splitting
+PUNCTUATION_SENTENCE = ".!?\u061f\u3002\uff01\uff1f"  # .!? .?. ??
+PUNCTUATION_SENTENCE_COMMA = ".!?,\u3001\u061f\u3002\uff01\uff0c\uff1f"  # .!?, ,. ??
+
+
+def process_subtitle_tokens(
+    tokens_with_timestamps: List[dict],
+    subtitle_entries: List[Tuple[float, float, str]],
+    max_subtitle_words: int,
+    subtitle_mode: str,
+    lang_code: str,
+    use_spacy_segmentation: bool = False,
+    fallback_end_time: Optional[float] = None,
+) -> None:
+    """Process TTS tokens into subtitle entries according to the subtitle mode.
+    
+    This function modifies subtitle_entries in-place by appending new entries.
+    
+    Args:
+        tokens_with_timestamps: List of token dictionaries with 'start', 'end', 'text',
+            and 'whitespace' keys.
+        subtitle_entries: List to append subtitle entries to (modified in-place).
+            Each entry is a tuple of (start_time, end_time, text).
+        max_subtitle_words: Maximum number of words per subtitle entry.
+        subtitle_mode: One of "Disabled", "Line", "Sentence", "Sentence + Comma",
+            "Sentence + Highlighting", or a string like "5" for word-count mode.
+        lang_code: Language code for spaCy processing (e.g., "a" for English).
+        use_spacy_segmentation: Whether to use spaCy for sentence boundary detection.
+        fallback_end_time: Fallback end time for the last entry if none is available.
+    """
+    if not tokens_with_timestamps:
+        return
+
+    processed_tokens = tokens_with_timestamps
+
+    # For English with spaCy enabled and sentence-based modes, use spaCy for sentence boundaries
+    # spaCy is disabled when subtitle mode is "Disabled" or "Line"
+    use_spacy_for_english = (
+        use_spacy_segmentation
+        and subtitle_mode not in ["Disabled", "Line"]
+        and lang_code in ["a", "b"]
+        and subtitle_mode in ["Sentence", "Sentence + Comma"]
+    )
+
+    if subtitle_mode == "Sentence + Highlighting":
+        _process_karaoke_highlighting(
+            processed_tokens, subtitle_entries, max_subtitle_words, fallback_end_time
+        )
+    elif subtitle_mode in ["Sentence", "Sentence + Comma", "Line"]:
+        if use_spacy_for_english and subtitle_mode != "Line":
+            _process_spacy_sentences(
+                processed_tokens, subtitle_entries, max_subtitle_words,
+                subtitle_mode, lang_code, fallback_end_time
+            )
+        else:
+            _process_regex_sentences(
+                processed_tokens, subtitle_entries, max_subtitle_words,
+                subtitle_mode, fallback_end_time
+            )
+    else:
+        # Word count-based grouping (e.g., "5" for 5-word groups)
+        _process_word_count(
+            processed_tokens, subtitle_entries, max_subtitle_words,
+            subtitle_mode, fallback_end_time
+        )
+
+
+def _process_karaoke_highlighting(
+    tokens: List[dict],
+    subtitle_entries: List[Tuple[float, float, str]],
+    max_subtitle_words: int,
+    fallback_end_time: Optional[float],
+) -> None:
+    """Process tokens for Sentence + Highlighting mode (karaoke effect)."""
+    separator = rf"[{re.escape(PUNCTUATION_SENTENCE)}]"
+    current_sentence = []
+    word_count = 0
+
+    for token in tokens:
+        current_sentence.append(token)
+        word_count += 1
+
+        # Split sentences based on separator or word count
+        if (
+            re.search(separator, token["text"]) and token.get("whitespace") == " "
+        ) or word_count >= max_subtitle_words:
+            if current_sentence:
+                # Create karaoke subtitle entry for this sentence
+                start_time = current_sentence[0]["start"]
+                end_time = current_sentence[-1]["end"]
+
+                # Generate karaoke text with timing
+                karaoke_text = ""
+                for t in current_sentence:
+                    # Calculate duration in centiseconds
+                    duration = (
+                        t["end"] - t["start"]
+                        if t.get("end") is not None and t.get("start") is not None
+                        else 0.5
+                    )
+                    duration_cs = int(duration * 100)
+                    # Add karaoke effect
+                    karaoke_text += f"{{\\kf{duration_cs}}}{t['text']}{t.get('whitespace', '') or ''}"
+
+                subtitle_entries.append(
+                    (start_time, end_time, karaoke_text.strip())
+                )
+                current_sentence = []
+                word_count = 0
+
+    # Add any remaining tokens as a sentence
+    if current_sentence:
+        start_time = current_sentence[0]["start"]
+        end_time = current_sentence[-1]["end"]
+
+        # Generate karaoke text for remaining tokens
+        karaoke_text = ""
+        for t in current_sentence:
+            duration = t["end"] - t["start"] if t.get("end") and t.get("start") else 0.5
+            duration_cs = int(duration * 100)
+            karaoke_text += f"{{\\kf{duration_cs}}}{t['text']}{t.get('whitespace', '') or ''}"
+        subtitle_entries.append((start_time, end_time, karaoke_text.strip()))
+
+    # Fallback for last entry
+    _apply_fallback_end_time(subtitle_entries, fallback_end_time)
+
+
+def _process_spacy_sentences(
+    tokens: List[dict],
+    subtitle_entries: List[Tuple[float, float, str]],
+    max_subtitle_words: int,
+    subtitle_mode: str,
+    lang_code: str,
+    fallback_end_time: Optional[float],
+) -> None:
+    """Process tokens using spaCy for sentence boundary detection."""
+    try:
+        from abogen.spacy_utils import get_spacy_model
+    except ImportError:
+        # Fall back to regex if spaCy is not available
+        _process_regex_sentences(
+            tokens, subtitle_entries, max_subtitle_words,
+            subtitle_mode, fallback_end_time
+        )
+        return
+
+    nlp = get_spacy_model(lang_code)
+    if not nlp:
+        _process_regex_sentences(
+            tokens, subtitle_entries, max_subtitle_words,
+            subtitle_mode, fallback_end_time
+        )
+        return
+
+    # Build full text and track character positions to token indices
+    full_text = ""
+    for token in tokens:
+        text_part = token["text"] + (token.get("whitespace") or "")
+        full_text += text_part
+
+    # Get sentence boundaries from spaCy
+    doc = nlp(full_text)
+    sentence_boundaries = [sent.end_char for sent in doc.sents]
+
+    # For "Sentence + Comma" mode, also split on commas
+    if subtitle_mode == "Sentence + Comma":
+        comma_positions = [
+            i + 1 for i, c in enumerate(full_text) if c == ","
+        ]
+        sentence_boundaries = sorted(
+            set(sentence_boundaries + comma_positions)
+        )
+
+    # Group tokens by sentence boundaries
+    current_sentence = []
+    word_count = 0
+    current_char_pos = 0
+    boundary_idx = 0
+
+    for token in tokens:
+        current_sentence.append(token)
+        word_count += 1
+        text_len = len(token["text"]) + len(token.get("whitespace") or "")
+        current_char_pos += text_len
+
+        # Check if we've hit a sentence boundary or max words
+        at_boundary = (
+            boundary_idx < len(sentence_boundaries)
+            and current_char_pos >= sentence_boundaries[boundary_idx]
+        )
+        if at_boundary or word_count >= max_subtitle_words:
+            if current_sentence:
+                start_time = current_sentence[0]["start"]
+                end_time = current_sentence[-1]["end"]
+                sentence_text = "".join(
+                    t["text"] + (t.get("whitespace") or "")
+                    for t in current_sentence
+                )
+                subtitle_entries.append(
+                    (start_time, end_time, sentence_text.strip())
+                )
+                current_sentence = []
+                word_count = 0
+            if at_boundary:
+                boundary_idx += 1
+
+    # Add remaining tokens
+    if current_sentence:
+        start_time = current_sentence[0]["start"]
+        end_time = current_sentence[-1]["end"]
+        sentence_text = "".join(
+            t["text"] + (t.get("whitespace") or "")
+            for t in current_sentence
+        )
+        subtitle_entries.append(
+            (start_time, end_time, sentence_text.strip())
+        )
+
+    # Fallback for last entry
+    _apply_fallback_end_time(subtitle_entries, fallback_end_time)
+
+
+def _process_regex_sentences(
+    tokens: List[dict],
+    subtitle_entries: List[Tuple[float, float, str]],
+    max_subtitle_words: int,
+    subtitle_mode: str,
+    fallback_end_time: Optional[float],
+) -> None:
+    """Process tokens using regex for sentence boundary detection."""
+    # Define separator pattern based on mode
+    if subtitle_mode == "Line":
+        separator = r"\n"
+    elif subtitle_mode == "Sentence":
+        # Use punctuation without comma
+        separator = rf"[{re.escape(PUNCTUATION_SENTENCE)}]"
+    else:  # Sentence + Comma
+        # Use punctuation with comma
+        separator = rf"[{re.escape(PUNCTUATION_SENTENCE_COMMA)}]"
+
+    current_sentence = []
+    word_count = 0
+
+    for token in tokens:
+        current_sentence.append(token)
+        word_count += 1
+
+        # Split sentences based on separator or word count
+        if (
+            re.search(separator, token["text"]) and token.get("whitespace") == " "
+        ) or word_count >= max_subtitle_words:
+            if current_sentence:
+                # Create subtitle entry for this sentence
+                start_time = current_sentence[0]["start"]
+                end_time = current_sentence[-1]["end"]
+
+                # Simplified text joining logic
+                sentence_text = ""
+                for t in current_sentence:
+                    sentence_text += t["text"] + (t.get("whitespace") or "")
+
+                subtitle_entries.append(
+                    (start_time, end_time, sentence_text.strip())
+                )
+                current_sentence = []
+                word_count = 0
+
+    # Add any remaining tokens as a sentence
+    if current_sentence:
+        start_time = current_sentence[0]["start"]
+        end_time = current_sentence[-1]["end"]
+
+        # Simplified text joining logic
+        sentence_text = ""
+        for t in current_sentence:
+            sentence_text += t["text"] + (t.get("whitespace") or "")
+        subtitle_entries.append((start_time, end_time, sentence_text.strip()))
+
+    # Fallback for last entry
+    _apply_fallback_end_time(subtitle_entries, fallback_end_time)
+
+
+def _process_word_count(
+    tokens: List[dict],
+    subtitle_entries: List[Tuple[float, float, str]],
+    max_subtitle_words: int,
+    subtitle_mode: str,
+    fallback_end_time: Optional[float],
+) -> None:
+    """Process tokens by counting spaces (word count mode)."""
+    try:
+        word_count = int(subtitle_mode.split()[0])
+        word_count = min(word_count, max_subtitle_words)
+    except (ValueError, IndexError):
+        word_count = 1
+
+    current_group = []
+    space_count = 0
+
+    for token in tokens:
+        current_group.append(token)
+
+        # Count spaces after tokens (in the whitespace field)
+        if token.get("whitespace", "") == " ":
+            space_count += 1
+
+            # Split after counting N spaces
+            if space_count >= word_count:
+                text = "".join(
+                    t["text"] + (t.get("whitespace") or "")
+                    for t in current_group
+                )
+                subtitle_entries.append(
+                    (
+                        current_group[0]["start"],
+                        current_group[-1]["end"],
+                        text.strip(),
+                    )
+                )
+                current_group = []
+                space_count = 0
+
+    # Add any remaining tokens
+    if current_group:
+        text = "".join(
+            t["text"] + (t.get("whitespace") or "") for t in current_group
+        )
+        subtitle_entries.append(
+            (current_group[0]["start"], current_group[-1]["end"], text.strip())
+        )
+
+    # Fallback for last entry
+    _apply_fallback_end_time(subtitle_entries, fallback_end_time)
+
+
+def _apply_fallback_end_time(
+    subtitle_entries: List[Tuple[float, float, str]],
+    fallback_end_time: Optional[float],
+) -> None:
+    """Apply fallback end time to the last entry if needed."""
+    if subtitle_entries and fallback_end_time is not None:
+        last_entry = subtitle_entries[-1]
+        start, end, text = last_entry
+        if end is None or end <= start or end <= 0:
+            subtitle_entries[-1] = (start, fallback_end_time, text)

abogen/domain/subtitle_processor.py

@@ -0,0 +1,279 @@
+"""Subtitle-to-audio processing pipeline.
+
+Converts subtitle files (SRT/ASS/VTT/timestamp text) into audio by
+generating TTS for each entry and mixing into a buffer.
+"""
+
+from __future__ import annotations
+
+import logging
+import time
+from dataclasses import dataclass
+from typing import Any, Callable, List, Optional, Tuple
+
+import numpy as np
+
+from abogen.domain.audio_buffer import (
+    create_silence,
+    fit_audio_to_duration,
+    ffmpeg_time_stretch,
+    mix_audio,
+    normalize_audio,
+    SAMPLE_RATE,
+)
+from abogen.domain.audio_helpers import to_float32
+from abogen.domain.progress import calc_etr_str
+from abogen.subtitle_utils import (
+    parse_ass_file,
+    parse_srt_file,
+    parse_vtt_file,
+    parse_timestamp_text_file,
+)
+
+logger = logging.getLogger(__name__)
+
+
+@dataclass
+class SubtitleEntry:
+    """A single subtitle entry with timing."""
+    start: float
+    end: Optional[float]
+    text: str
+
+
+def parse_subtitle_file(
+    file_path: str,
+    is_timestamp_text: bool = False,
+) -> List[Tuple[float, Optional[float], str]]:
+    """Parse a subtitle file into (start, end, text) tuples.
+
+    Args:
+        file_path: Path to subtitle file.
+        is_timestamp_text: Whether to treat as timestamp text file.
+
+    Returns:
+        List of (start_time, end_time, text) tuples.
+    """
+    if is_timestamp_text:
+        return parse_timestamp_text_file(file_path)
+
+    import os
+    ext = os.path.splitext(file_path)[1].lower()
+    if ext == ".srt":
+        return parse_srt_file(file_path)
+    elif ext == ".vtt":
+        return parse_vtt_file(file_path)
+    else:
+        return parse_ass_file(file_path)
+
+
+def format_time_range(
+    start: float,
+    end: Optional[float],
+    is_auto_end: bool = False,
+) -> str:
+    """Format a time range for display in logs.
+
+    Args:
+        start: Start time in seconds.
+        end: End time in seconds, or None.
+        is_auto_end: Whether end time is auto-detected.
+
+    Returns:
+        Formatted string like "00:01:23,456 - 00:01:25,789" or "00:01:23 - AUTO".
+    """
+    def _fmt(seconds: float) -> str:
+        h = int(seconds // 3600)
+        m = int(seconds % 3600 // 60)
+        s = int(seconds % 60)
+        ms = int((seconds - int(seconds)) * 1000)
+        result = f"{h:02d}:{m:02d}:{s:02d}"
+        if ms > 0:
+            result += f",{ms:03d}"
+        return result
+
+    if is_auto_end or end is None:
+        return f"{_fmt(start)} - AUTO"
+    return f"{_fmt(start)} - {_fmt(end)}"
+
+
+def speed_up_audio(
+    audio: np.ndarray,
+    speed_factor: float,
+    method: str = "tts",
+    *,
+    backend: Any = None,
+    text: str = "",
+    voice: Any = None,
+    base_speed: float = 1.0,
+    sample_rate: int = SAMPLE_RATE,
+) -> np.ndarray:
+    """Speed up audio to fit a time window.
+
+    Args:
+        audio: Input audio buffer.
+        speed_factor: Required speed multiplier.
+        method: "ffmpeg" for time-stretch, "tts" for regeneration.
+        backend: TTS backend (required if method="tts").
+        text: Text to regenerate (required if method="tts").
+        voice: Voice to use for regeneration.
+        base_speed: Base speed for TTS.
+        sample_rate: Sample rate.
+
+    Returns:
+        Speed-adjusted audio buffer.
+    """
+    if speed_factor <= 1.0:
+        return audio
+
+    if method == "ffmpeg":
+        logger.info("FFmpeg time-stretch: %.2fx", speed_factor)
+        return ffmpeg_time_stretch(audio, speed_factor, sample_rate)
+
+    # TTS regeneration
+    if backend is None:
+        return audio
+    new_speed = base_speed * speed_factor
+    logger.info("Regenerating at %.2fx speed", new_speed)
+    results = [
+        r for r in backend(text, voice=voice, speed=new_speed, split_pattern=None)
+    ]
+    chunks = [r.audio for r in results]
+    if not chunks:
+        return audio
+    return np.concatenate([to_float32(c) for c in chunks])
+
+
+def process_subtitle_entries(
+    subtitles: List[Tuple[float, Optional[float], str]],
+    *,
+    backend: Any,
+    voice: Any,
+    speed: float = 1.0,
+    cancel_check: Callable[[], bool] = lambda: False,
+    log_callback: Optional[Callable[[str], None]] = None,
+    progress_callback: Optional[Callable[[int, str], None]] = None,
+    replace_newlines: bool = True,
+    use_gaps: bool = False,
+    is_timestamp_text: bool = False,
+    subtitle_speed_method: str = "tts",
+    sample_rate: int = SAMPLE_RATE,
+) -> np.ndarray:
+    """Process subtitle entries: generate TTS for each and mix into buffer.
+
+    This is the core domain logic for subtitle-to-audio conversion.
+    UI-specific concerns (signals, widgets) are handled via callbacks.
+
+    Args:
+        subtitles: List of (start, end, text) tuples.
+        backend: TTS pipeline callable.
+        voice: Resolved voice for TTS.
+        speed: TTS speed.
+        cancel_check: Returns True if processing should stop.
+        log_callback: Called with log messages.
+        progress_callback: Called with (percent, etr_string).
+        replace_newlines: Replace \\n with spaces in text.
+        use_gaps: Whether to use silent gaps between subtitles.
+        is_timestamp_text: Whether input is timestamp text.
+        subtitle_speed_method: "ffmpeg" or "tts" for speed adjustment.
+        sample_rate: Audio sample rate.
+
+    Returns:
+        Mixed audio buffer (float32).
+    """
+    if not subtitles:
+        return np.array([], dtype="float32")
+
+    max_end = max((end for _, end, _ in subtitles if end is not None), default=0)
+    buffer_samples = int(max_end * sample_rate) + sample_rate
+    audio_buffer = np.zeros(buffer_samples, dtype="float32")
+    etr_start = time.time()
+    total = len(subtitles)
+
+    for idx, (start_time, end_time, text) in enumerate(subtitles, 1):
+        if cancel_check():
+            break
+
+        processed_text = text.replace("\n", " ") if replace_newlines else text
+        next_start = (
+            subtitles[idx][0]
+            if (use_gaps and idx < total)
+            else float("inf")
+        )
+        subtitle_duration = None if end_time is None else end_time - start_time
+
+        is_auto_end = is_timestamp_text or (use_gaps and idx == total) or end_time is None
+        if log_callback:
+            log_callback(
+                f"\n[{idx}/{total}] {format_time_range(start_time, end_time, is_auto_end)}: {processed_text}"
+            )
+
+        # Generate TTS
+        results = [
+            r for r in backend(
+                processed_text, voice=voice, speed=speed, split_pattern=None
+            )
+            if not cancel_check()
+        ]
+        if cancel_check():
+            break
+
+        audio_chunks = [r.audio for r in results]
+        full_audio = (
+            np.concatenate([to_float32(a) for a in audio_chunks])
+            if audio_chunks
+            else np.zeros(int((subtitle_duration or 0) * sample_rate), dtype="float32")
+        )
+        audio_duration = len(full_audio) / sample_rate
+
+        # Timing adjustment
+        if is_timestamp_text:
+            end_time = start_time + audio_duration
+            subtitle_duration = audio_duration
+        elif use_gaps:
+            end_time = min(start_time + audio_duration, next_start)
+            subtitle_duration = end_time - start_time
+        elif subtitle_duration is None:
+            subtitle_duration = audio_duration
+            end_time = start_time + audio_duration
+
+        # Speed up if needed
+        speedup_threshold = next_start - start_time if use_gaps else subtitle_duration
+        if audio_duration > speedup_threshold and speedup_threshold > 0:
+            speed_factor = audio_duration / speedup_threshold
+            full_audio = speed_up_audio(
+                full_audio, speed_factor,
+                method=subtitle_speed_method,
+                backend=backend, text=processed_text,
+                voice=voice, base_speed=speed,
+                sample_rate=sample_rate,
+            )
+            audio_duration = len(full_audio) / sample_rate
+
+        # Adjust duration after speed change
+        if use_gaps:
+            end_time = min(start_time + audio_duration, next_start)
+            subtitle_duration = end_time - start_time
+        elif subtitle_duration is None:
+            subtitle_duration = audio_duration
+            end_time = start_time + audio_duration
+
+        # Pad or trim to subtitle duration
+        full_audio = fit_audio_to_duration(full_audio, subtitle_duration, sample_rate)
+
+        # Mix into buffer
+        start_sample = int(start_time * sample_rate)
+        audio_buffer = mix_audio(audio_buffer, full_audio, start_sample)
+
+        # Progress
+        if progress_callback:
+            percent = min(int(idx / total * 100), 99)
+            etr = calc_etr_str(time.time() - etr_start, idx, total)
+            progress_callback(percent, etr)
+
+    # Normalize if needed
+    if np.abs(audio_buffer).max() > 1.0:
+        logger.info("Normalizing audio (peak: %.2f)", np.abs(audio_buffer).max())
+        audio_buffer = normalize_audio(audio_buffer)
+
+    return audio_buffer

abogen/domain/text_chapters.py

@@ -0,0 +1,59 @@
+"""Chapter parsing from raw text.
+
+Provides a unified function for splitting text by chapter markers,
+used by both WebUI and PyQt conversion runners.
+"""
+
+from __future__ import annotations
+
+import re
+from typing import List, Tuple
+
+from abogen.subtitle_utils import clean_text
+
+
+_CHAPTER_MARKER_RE = re.compile(r"<<CHAPTER_MARKER:(.*?)>>", re.IGNORECASE)
+
+
+def parse_chapters_from_text(
+    text: str,
+    default_title: str = "text",
+    clean: bool = True,
+) -> List[Tuple[str, str]]:
+    """Split raw text into chapters using chapter marker patterns.
+
+    Preserves content before the first marker as "Introduction" if present.
+    Optionally applies clean_text() to each chapter segment.
+
+    Args:
+        text: Raw text possibly containing <<CHAPTER_MARKER:Title>> markers.
+        default_title: Fallback title when no markers are found.
+        clean: Whether to apply clean_text() to each segment.
+
+    Returns:
+        List of (title, text) tuples.
+    """
+    matches = list(_CHAPTER_MARKER_RE.finditer(text))
+    if not matches:
+        cleaned = clean_text(text) if clean else text
+        return [(default_title, cleaned)]
+
+    chapters: List[Tuple[str, str]] = []
+
+    # Preserve content before first marker as "Introduction"
+    first_start = matches[0].start()
+    if first_start > 0:
+        intro_text = text[:first_start].strip()
+        if intro_text:
+            chapters.append(("Introduction", clean_text(intro_text) if clean else intro_text))
+
+    for idx, match in enumerate(matches):
+        start = match.end()
+        end = matches[idx + 1].start() if idx + 1 < len(matches) else len(text)
+        chapter_name = match.group(1).strip() or default_title
+        chapter_text = text[start:end].strip()
+        if clean:
+            chapter_text = clean_text(chapter_text)
+        chapters.append((chapter_name, chapter_text))
+
+    return chapters

abogen/domain/title_builder.py

@@ -0,0 +1,97 @@
+from __future__ import annotations
+
+from pathlib import Path
+from typing import Any, Dict, List, Mapping, Optional
+
+from .metadata_helpers import (
+    ensure_sentence,
+    extract_series_metadata,
+    format_author_sentence,
+    format_series_sentence,
+    normalize_metadata_map,
+)
+
+
+def build_title_intro_text(
+    metadata: Optional[Mapping[str, Any]],
+    fallback_basename: str,
+) -> str:
+    """Build the title introduction text from metadata."""
+    normalized = normalize_metadata_map(metadata)
+    fallback_title = Path(fallback_basename).stem if fallback_basename else ""
+    title = (
+        normalized.get("title")
+        or normalized.get("book_title")
+        or normalized.get("album")
+        or fallback_title
+    )
+    if not title:
+        title = fallback_title
+    subtitle = normalized.get("subtitle") or normalized.get("sub_title")
+    if subtitle and title and subtitle.casefold() == title.casefold():
+        subtitle = ""
+
+    author_value = ""
+    for candidate in ("artist", "album_artist", "author", "authors", "writer", "composer"):
+        value = normalized.get(candidate)
+        if value:
+            author_value = value
+            break
+
+    series_name, series_number = extract_series_metadata(normalized)
+    series_sentence = format_series_sentence(series_name, series_number)
+
+    sentences: List[str] = []
+    if series_sentence:
+        sentences.append(ensure_sentence(series_sentence))
+    if title:
+        sentences.append(ensure_sentence(title))
+    if subtitle:
+        sentences.append(ensure_sentence(subtitle))
+    author_sentence = format_author_sentence(author_value)
+    if author_sentence:
+        sentences.append(ensure_sentence(author_sentence))
+    return " ".join(sentences).strip()
+
+
+def build_outro_text(
+    metadata: Optional[Mapping[str, Any]],
+    fallback_basename: str,
+) -> str:
+    """Build the outro/closing text from metadata."""
+    normalized = normalize_metadata_map(metadata)
+    fallback_title = Path(fallback_basename).stem if fallback_basename else ""
+    title = (
+        normalized.get("title")
+        or normalized.get("book_title")
+        or normalized.get("album")
+        or fallback_title
+    )
+    author_value = ""
+    for candidate in ("authors", "author", "album_artist", "artist", "writer", "composer"):
+        value = normalized.get(candidate)
+        if value:
+            author_value = value
+            break
+    author_sentence = format_author_sentence(author_value)
+    authors_fragment = (
+        author_sentence[3:].strip() if author_sentence.lower().startswith("by ") else author_sentence.strip()
+    )
+
+    if title and authors_fragment:
+        closing_line = f"The end of {title} from {authors_fragment}"
+    elif title:
+        closing_line = f"The end of {title}"
+    elif authors_fragment:
+        closing_line = f"The end from {authors_fragment}"
+    else:
+        closing_line = "The end"
+
+    series_name, series_number = extract_series_metadata(normalized)
+    series_sentence = format_series_sentence(series_name, series_number)
+
+    sentences: List[str] = [ensure_sentence(closing_line)]
+    if series_sentence:
+        sentences.append(ensure_sentence(series_sentence))
+
+    return " ".join(sentence for sentence in sentences if sentence).strip()

abogen/domain/tokens.py

@@ -0,0 +1,13 @@
+"""Shared token stubs for TTS processing."""
+
+from __future__ import annotations
+
+
+class FakeToken:
+    """Minimal token stub for languages without per-word token support."""
+
+    def __init__(self, text: str, start: float, end: float):
+        self.text = text
+        self.start_ts = start
+        self.end_ts = end
+        self.whitespace = ""

abogen/domain/voice_loader.py

@@ -0,0 +1,124 @@
+"""Voice loading and caching utilities.
+
+This module provides unified voice loading with caching support for both
+PyQt and WebUI interfaces.
+"""
+
+from __future__ import annotations
+
+from typing import Any, Dict, Optional, Tuple
+
+from abogen.voice_formulas import get_new_voice
+
+
+class VoiceCache:
+    """Thread-safe voice cache for loaded voice tensors."""
+    
+    def __init__(self):
+        self._cache: Dict[str, Any] = {}
+    
+    def get(self, voice_spec: str) -> Optional[Any]:
+        """Get cached voice by spec."""
+        return self._cache.get(voice_spec)
+    
+    def set(self, voice_spec: str, voice: Any) -> None:
+        """Cache a loaded voice."""
+        self._cache[voice_spec] = voice
+    
+    def contains(self, voice_spec: str) -> bool:
+        """Check if voice is in cache."""
+        return voice_spec in self._cache
+    
+    def clear(self) -> None:
+        """Clear all cached voices."""
+        self._cache.clear()
+    
+    def __contains__(self, voice_spec: str) -> bool:
+        return self.contains(voice_spec)
+
+
+def resolve_voice(
+    voice_spec: str,
+    pipeline: Any,
+    use_gpu: bool,
+    cache: Optional[VoiceCache] = None,
+) -> Any:
+    """Resolve voice spec to actual voice tensor or name.
+    
+    If voice_spec contains '*' (formula), loads the voice using get_new_voice.
+    Otherwise, returns the voice_spec as-is (it's a voice name).
+    
+    Uses optional cache to avoid reloading same voice multiple times.
+    
+    Args:
+        voice_spec: Voice specification (name or formula string with '*').
+        pipeline: TTS pipeline instance for loading formula voices.
+        use_gpu: Whether to use GPU for voice loading.
+        cache: Optional VoiceCache instance for caching loaded voices.
+        
+    Returns:
+        Loaded voice tensor (for formulas) or voice name string.
+    """
+    # Check cache first
+    if cache and cache.contains(voice_spec):
+        return cache.get(voice_spec)
+
+    # Load voice
+    if "*" in voice_spec:
+        if pipeline is None or not hasattr(pipeline, "load_single_voice"):
+            return voice_spec
+        loaded_voice = get_new_voice(pipeline, voice_spec, use_gpu)
+    else:
+        loaded_voice = voice_spec
+    
+    # Cache it
+    if cache:
+        cache.set(voice_spec, loaded_voice)
+    
+    return loaded_voice
+
+
+def load_voice_cached(
+    voice_name: str,
+    pipeline: Any,
+    use_gpu: bool,
+    cache: Any = None,
+) -> Any:
+    """Load voice with caching (compatibility wrapper for PyQt).
+
+    This function maintains backward compatibility with the PyQt interface
+    while using the unified voice loading logic.
+
+    Args:
+        voice_name: Voice name or formula string.
+        pipeline: TTS pipeline instance.
+        use_gpu: Whether to use GPU.
+        cache: Optional VoiceCache or dict to use as cache.
+
+    Returns:
+        Loaded voice tensor or voice name string.
+    """
+    # Check cache (supports both VoiceCache and plain dict)
+    if cache is not None:
+        if isinstance(cache, VoiceCache):
+            if cache.contains(voice_name):
+                return cache.get(voice_name)
+        elif voice_name in cache:
+            return cache[voice_name]
+
+    # Load voice
+    if "*" in voice_name:
+        if pipeline is None or not hasattr(pipeline, "load_single_voice"):
+            return voice_name
+        loaded_voice = get_new_voice(pipeline, voice_name, use_gpu)
+    else:
+        loaded_voice = voice_name
+
+    # Cache it
+    if cache is not None:
+        if isinstance(cache, VoiceCache):
+            cache.set(voice_name, loaded_voice)
+        else:
+            cache[voice_name] = loaded_voice
+
+    return loaded_voice

abogen/domain/voice_resolution.py

@@ -0,0 +1,190 @@
+"""Voice resolution helpers.
+
+Functions for resolving voice specifications, collecting required voice IDs,
+and determining the voice to use for chapters and chunks.
+"""
+
+from __future__ import annotations
+
+from typing import Any, Dict, Optional, Set
+
+from abogen.tts_plugin.utils import get_voices, get_default_voice
+from abogen.voice_formulas import extract_voice_ids
+from abogen.voice_cache import ensure_voice_assets
+
+
+def spec_to_voice_ids(spec: Any) -> Set[str]:
+    text = str(spec or "").strip()
+    if not text:
+        return set()
+    if text == "__custom_mix":
+        return set()
+    if "*" in text:
+        try:
+            return set(extract_voice_ids(text))
+        except ValueError:
+            return set()
+    if text in get_voices("kokoro"):
+        return {text}
+    return set()
+
+
+def job_voice_fallback(job: Any) -> str:
+    base = str(getattr(job, "voice", "") or "").strip()
+    if base and base != "__custom_mix":
+        return base
+
+    speakers = getattr(job, "speakers", None)
+    if isinstance(speakers, dict):
+        narrator = speakers.get("narrator")
+        if isinstance(narrator, dict):
+            for key in ("resolved_voice", "voice_formula", "voice"):
+                value = narrator.get(key)
+                candidate = str(value or "").strip()
+                if candidate and candidate != "__custom_mix":
+                    return candidate
+        for payload in speakers.values() or []:
+            if not isinstance(payload, dict):
+                continue
+            for key in ("resolved_voice", "voice_formula", "voice"):
+                value = payload.get(key)
+                candidate = str(value or "").strip()
+                if candidate and candidate != "__custom_mix":
+                    return candidate
+
+    for chapter in getattr(job, "chapters", []) or []:
+        if not isinstance(chapter, dict):
+            continue
+        for key in ("resolved_voice", "voice_formula", "voice"):
+            candidate = str(chapter.get(key) or "").strip()
+            if candidate and candidate != "__custom_mix":
+                return candidate
+
+    return ""
+
+
+def collect_required_voice_ids(job: Any) -> Set[str]:
+    voices: Set[str] = set()
+    voices.update(spec_to_voice_ids(job.voice))
+    voices.update(spec_to_voice_ids(job_voice_fallback(job)))
+
+    for chapter in getattr(job, "chapters", []) or []:
+        if not isinstance(chapter, dict):
+            continue
+        for key in ("resolved_voice", "voice_formula", "voice"):
+            voices.update(spec_to_voice_ids(chapter.get(key)))
+
+    for chunk in getattr(job, "chunks", []) or []:
+        if not isinstance(chunk, dict):
+            continue
+        for key in ("resolved_voice", "voice_formula", "voice"):
+            voices.update(spec_to_voice_ids(chunk.get(key)))
+
+    speakers = getattr(job, "speakers", {})
+    if isinstance(speakers, dict):
+        for payload in speakers.values() or []:
+            if not isinstance(payload, dict):
+                continue
+            for key in ("resolved_voice", "voice_formula", "voice"):
+                voices.update(spec_to_voice_ids(payload.get(key)))
+
+    voices.update(get_voices("kokoro"))
+    return voices
+
+
+def initialize_voice_cache(job: Any) -> None:
+    try:
+        targets = collect_required_voice_ids(job)
+        downloaded, errors = ensure_voice_assets(
+            targets,
+            on_progress=lambda message: job.add_log(message, level="debug"),
+        )
+    except RuntimeError as exc:
+        job.add_log(f"Voice cache unavailable: {exc}", level="warning")
+        return
+
+    if downloaded:
+        job.add_log(
+            f"Cached {len(downloaded)} voice asset{'s' if len(downloaded) != 1 else ''} locally.",
+            level="info",
+        )
+
+    for voice_id, error in errors.items():
+        job.add_log(f"Failed to cache voice '{voice_id}': {error}", level="warning")
+
+
+def chapter_voice_spec(job: Any, override: Optional[Dict[str, Any]]) -> str:
+    if not override:
+        return job_voice_fallback(job)
+
+    resolved = str(override.get("resolved_voice", "")).strip()
+    if resolved:
+        return resolved
+
+    formula = str(override.get("voice_formula", "")).strip()
+    if formula:
+        return formula
+
+    voice = str(override.get("voice", "")).strip()
+    if voice:
+        return voice
+
+    return job_voice_fallback(job)
+
+
+def chunk_voice_spec(job: Any, chunk: Dict[str, Any], fallback: str) -> str:
+    for key in ("resolved_voice", "voice_formula", "voice"):
+        value = chunk.get(key)
+        if value:
+            return str(value)
+
+    speaker_id = chunk.get("speaker_id")
+    speakers = getattr(job, "speakers", None)
+    if isinstance(speakers, dict) and speaker_id in speakers:
+        speaker_entry = speakers.get(speaker_id) or {}
+        if isinstance(speaker_entry, dict):
+            for key in ("resolved_voice", "voice_formula", "voice"):
+                value = speaker_entry.get(key)
+                if value:
+                    return str(value)
+            profile_formula = speaker_entry.get("voice_formula")
+            if profile_formula:
+                return str(profile_formula)
+
+    profile_name = chunk.get("voice_profile")
+    if profile_name:
+        if isinstance(speakers, dict):
+            speaker_entry = speakers.get(profile_name)
+            if isinstance(speaker_entry, dict):
+                for key in ("resolved_voice", "voice_formula", "voice"):
+                    value = speaker_entry.get(key)
+                    if value:
+                        return str(value)
+
+    if fallback:
+        return fallback
+    return job_voice_fallback(job)
+
+
+def resolve_fallback_voice_spec(
+    base_spec: str,
+    job_voice: str,
+    voice_cache_keys: list[str],
+    provider: str = "kokoro",
+) -> str:
+    """Resolve the voice spec for intro/outro with a priority fallback chain.
+
+    Priority: base_spec → job_voice → first voice_cache key → default voice.
+    ``"__custom_mix"`` is treated as empty (it is not a usable voice spec).
+    """
+    spec = base_spec or job_voice
+    if spec == "__custom_mix":
+        spec = job_voice or ""
+    if not spec:
+        for key in voice_cache_keys:
+            if key and key != "__custom_mix":
+                spec = key.split(":", 1)[-1]
+                break
+    if not spec:
+        spec = get_default_voice(provider)
+    return spec

abogen/domain/voice_utils.py

@@ -0,0 +1,130 @@
+from __future__ import annotations
+
+from typing import Any, Dict, Mapping, Optional, Tuple, Set
+
+from abogen.voice_formulas import extract_voice_ids, get_new_voice
+from abogen.tts_plugin.utils import get_voices
+
+
+def infer_provider_from_spec(value: Any, fallback: str = "kokoro") -> str:
+    """Infer TTS provider from voice specification."""
+    raw = str(value or "").strip()
+    if not raw:
+        return fallback
+    if raw.upper() == raw and raw.replace("_", "").isalnum():
+        return "supertonic"
+    if raw == "__custom_mix" or "*" in raw or "+" in raw:
+        return "kokoro"
+    if raw in get_voices("kokoro"):
+        return "kokoro"
+    return fallback
+
+
+def supertonic_voice_from_spec(spec: Any, fallback: str) -> str:
+    """Normalize a voice specification for Supertonic.
+
+    This function only performs Supertonic-specific normalization (uppercase conversion
+    and fallback handling). Backend resolution is handled by the registry.
+    """
+    raw = str(spec or "").strip()
+    fallback_raw = str(fallback or "").strip()
+
+    # Normalize to uppercase for Supertonic voice IDs
+    upper = raw.upper() if raw else ""
+
+    # If empty or contains formula characters, use fallback
+    if not upper or "*" in upper or "+" in upper:
+        upper = fallback_raw.upper() if fallback_raw else ""
+
+    # If still empty, use default Supertonic voice
+    if not upper or "*" in upper or "+" in upper:
+        upper = "M1"
+
+    return upper
+
+
+def split_speaker_reference(value: Any) -> Tuple[Optional[str], str]:
+    """Parse speaker/profile reference from string.
+
+    Expected format: "speaker:name" or "profile:name"
+    Returns (name, original) or (None, original) if not a valid reference.
+    """
+    raw = str(value or "").strip()
+    if not raw or ":" not in raw:
+        return None, raw
+    prefix, remainder = raw.split(":", 1)
+    prefix = prefix.strip().lower()
+    if prefix not in {"speaker", "profile"}:
+        return None, raw
+    name = remainder.strip()
+    return (name or None), raw
+
+
+def formula_from_kokoro_entry(entry: Mapping[str, Any]) -> str:
+    """Build voice formula string from kokoro entry."""
+    voices = entry.get("voices") or []
+    if not voices:
+        return ""
+    total = 0.0
+    parts: list[tuple[str, float]] = []
+    for item in voices:
+        if not isinstance(item, (list, tuple)) or len(item) < 2:
+            continue
+        name = str(item[0] or "").strip()
+        try:
+            weight = float(item[1])
+        except (TypeError, ValueError):
+            continue
+        if name and weight > 0:
+            parts.append((name, weight))
+            total += weight
+
+    if not parts:
+        return ""
+
+    normalized = [(name, weight / total) for name, weight in parts]
+    return " + ".join(f"{name}*{weight:.6f}" for name, weight in normalized)
+
+
+def coerce_truthy(value: Any, default: bool = True) -> bool:
+    """Coerce a value to boolean with default."""
+    if isinstance(value, bool):
+        return value
+    if isinstance(value, str):
+        return value.lower() not in {"false", "0", "no", "off", ""}
+    if value is None:
+        return default
+    return bool(value)
+
+
+def resolve_voice_target(
+    raw_spec: str,
+    normalized_profiles: Dict[str, Dict[str, Any]],
+    *,
+    job_voice: str = "M1",
+    job_tts_provider: str = "kokoro",
+    job_supertonic_total_steps: int = 5,
+    job_speed: float = 1.0,
+) -> Tuple[str, str, Optional[float], Optional[int]]:
+    """Resolve a raw voice spec into (provider, voice_spec, speed_override, steps_override).
+
+    Pure function — all dependencies are passed as parameters.
+    """
+    spec = str(raw_spec or "").strip()
+    speaker_name, _ = split_speaker_reference(spec)
+    if speaker_name and speaker_name in normalized_profiles:
+        entry = normalized_profiles[speaker_name]
+        provider = str(entry.get("provider") or "kokoro").strip().lower() or "kokoro"
+        if provider == "supertonic":
+            voice = str(entry.get("voice") or job_voice or "M1").strip() or "M1"
+            steps = int(entry.get("total_steps") or job_supertonic_total_steps or 5)
+            speed = float(entry.get("speed") or job_speed or 1.0)
+            return "supertonic", supertonic_voice_from_spec(voice, job_voice), speed, steps
+        formula = formula_from_kokoro_entry(entry)
+        return "kokoro", formula or spec, None, None
+
+    fallback_provider = str(job_tts_provider or "kokoro").strip().lower() or "kokoro"
+    inferred = infer_provider_from_spec(spec, fallback=fallback_provider)
+    if inferred == "supertonic":
+        return "supertonic", supertonic_voice_from_spec(spec, job_voice), None, None
+    return "kokoro", spec, None, None

abogen/infrastructure/exporters.py

@@ -0,0 +1,447 @@
+from __future__ import annotations
+
+import json
+import logging
+import tempfile
+from dataclasses import dataclass
+from pathlib import Path
+from typing import Any, Dict, List, Optional, Mapping, Sequence
+
+import static_ffmpeg
+
+from abogen.domain.metadata_helpers import (
+    normalize_metadata_casefold,
+    split_people_field,
+    split_simple_list,
+    first_nonempty,
+    extract_year,
+    normalize_series_sequence,
+    build_audiobookshelf_metadata as _build_abs_metadata,
+    load_audiobookshelf_chapters as _load_abs_chapters,
+    _SERIES_SEQUENCE_TAG_KEYS,
+)
+from abogen.epub3.exporter import build_epub3_package
+from abogen.integrations.audiobookshelf import (
+    AudiobookshelfClient,
+    AudiobookshelfConfig,
+    AudiobookshelfUploadError,
+)
+from abogen.utils import create_process
+
+logger = logging.getLogger(__name__)
+
+
+@dataclass
+class ExportConfig:
+    """Configuration for export operations."""
+    ffmpeg_path: str = "ffmpeg"
+    verify_ssl: bool = True
+
+
+class ExportService:
+    """Unified service for audiobook exports (M4B, FFMETADATA, EPUB3, Audiobookshelf)."""
+    
+    def __init__(self, config: Optional[ExportConfig] = None):
+        self.config = config or ExportConfig()
+        static_ffmpeg.add_paths()
+    
+    # ----------------------------------------------------------------------
+    # FFMETADATA
+    # ----------------------------------------------------------------------
+    
+    def render_ffmetadata(
+        self,
+        metadata: Dict[str, Any],
+        chapters: List[Dict[str, Any]],
+    ) -> str:
+        """Render FFMETADATA content."""
+        lines = [";FFMETADATA1"]
+        
+        for key, value in (metadata or {}).items():
+            if value is None:
+                continue
+            key_str = str(key).strip()
+            if not key_str:
+                continue
+            lines.append(f"{key_str}={self._escape_ffmetadata_value(value)}")
+        
+        for chapter in chapters or []:
+            start = chapter.get("start")
+            end = chapter.get("end")
+            if start is None or end is None:
+                continue
+            try:
+                start_ms = max(0, int(round(float(start) * 1000)))
+                end_ms = int(round(float(end) * 1000))
+            except (TypeError, ValueError):
+                continue
+            if end_ms <= start_ms:
+                end_ms = start_ms + 1
+            lines.append("[CHAPTER]")
+            lines.append("TIMEBASE=1/1000")
+            lines.append(f"START={start_ms}")
+            lines.append(f"END={end_ms}")
+            title = chapter.get("title")
+            if title:
+                lines.append(f"title={self._escape_ffmetadata_value(title)}")
+            voice = chapter.get("voice")
+            if voice:
+                lines.append(f"voice={self._escape_ffmetadata_value(voice)}")
+        
+        return "\n".join(lines) + "\n"
+    
+    @staticmethod
+    def _escape_ffmetadata_value(value: Any) -> str:
+        escaped = str(value).replace("\\", "\\\\").replace("\n", "\\n")
+        escaped = escaped.replace("=", "\\=").replace(";", "\\;").replace("#", "\\#")
+        return escaped
+    
+    def write_ffmetadata_file(
+        self,
+        audio_path: Path,
+        metadata: Dict[str, Any],
+        chapters: List[Dict[str, Any]],
+    ) -> Optional[Path]:
+        """Write FFMETADATA file to temp location."""
+        content = self.render_ffmetadata(metadata, chapters)
+        if content.strip() == ";FFMETADATA1":
+            return None
+        
+        directory = audio_path.parent if audio_path.parent.exists() else Path(tempfile.gettempdir())
+        with tempfile.NamedTemporaryFile(
+            mode="w",
+            encoding="utf-8",
+            suffix=".ffmeta",
+            delete=False,
+            dir=str(directory),
+        ) as handle:
+            handle.write(content)
+            return Path(handle.name)
+    
+    # ----------------------------------------------------------------------
+    # M4B Export
+    # ----------------------------------------------------------------------
+    
+    def embed_m4b_metadata(
+        self,
+        audio_path: Path,
+        metadata: Dict[str, Any],
+        chapters: List[Dict[str, Any]],
+        cover_path: Optional[Path] = None,
+        cover_mime: Optional[str] = None,
+        log_callback: Optional[callable] = None,
+    ) -> None:
+        """Embed metadata and chapters into M4B file using FFmpeg + Mutagen."""
+        ffmetadata_path = self.write_ffmetadata_file(audio_path, metadata, chapters)
+        
+        metadata_args = self._metadata_to_ffmpeg_args(metadata)
+        
+        cmd = ["ffmpeg", "-y", "-i", str(audio_path)]
+        
+        if ffmetadata_path:
+            cmd.extend(["-f", "ffmetadata", "-i", str(ffmetadata_path)])
+        
+        if cover_path and cover_path.exists():
+            cmd.extend(["-i", str(cover_path)])
+            cmd.extend(["-map", "0:a"])
+            cmd.extend(["-map", "1:v:0", "-c:v:0", "mjpeg", "-disposition:v:0", "attached_pic"])
+            if cover_mime:
+                cmd.extend(["-metadata:s:v:0", f"mimetype={cover_mime}"])
+            cmd.extend(["-metadata:s:v:0", "title=Cover Art"])
+        else:
+            cmd.extend(["-map", "0:a"])
+        
+        cmd.extend(["-c:a", "copy"])
+        
+        if ffmetadata_path:
+            cmd.extend(["-map_metadata", "1", "-map_chapters", "1"])
+        else:
+            cmd.extend(["-map_metadata", "0"])
+        
+        if metadata_args:
+            cmd.extend(metadata_args)
+        
+        cmd.extend(["-movflags", "+faststart+use_metadata_tags"])
+        
+        temp_output = audio_path.with_suffix(audio_path.suffix + ".tmp")
+        if audio_path.suffix.lower() in {".m4b", ".mp4", ".m4a"}:
+            cmd.extend(["-f", "mp4"])
+        cmd.append(str(temp_output))
+        
+        if log_callback:
+            log_callback("Embedding metadata into M4B output")
+        
+        process = create_process(cmd, text=True)
+        return_code = process.wait()
+        
+        if ffmetadata_path and ffmetadata_path.exists():
+            try:
+                ffmetadata_path.unlink()
+            except OSError:
+                pass
+        
+        if return_code != 0:
+            if temp_output.exists():
+                temp_output.unlink(missing_ok=True)
+            raise RuntimeError(f"ffmpeg failed to embed metadata (exit code {return_code})")
+        
+        temp_output.replace(audio_path)
+        
+        if log_callback:
+            log_callback("Embedded metadata and chapters into M4B output", "info")
+        
+        # Apply chapters via Mutagen for better compatibility
+        self._apply_m4b_chapters_mutagen(audio_path, chapters, log_callback)
+    
+    @staticmethod
+    def _metadata_to_ffmpeg_args(metadata: Dict[str, Any]) -> List[str]:
+        args = []
+        for key, value in (metadata or {}).items():
+            if value in (None, ""):
+                continue
+            key_str = str(key).strip()
+            if not key_str:
+                continue
+            normalized_key = key_str.lower()
+            if normalized_key == "year":
+                ffmpeg_key = "date"
+            else:
+                ffmpeg_key = key_str
+            args.extend(["-metadata", f"{ffmpeg_key}={value}"])
+        return args
+    
+    def _apply_m4b_chapters_mutagen(
+        self,
+        audio_path: Path,
+        chapters: List[Dict[str, Any]],
+        log_callback: Optional[callable] = None,
+    ) -> bool:
+        """Apply chapter atoms using Mutagen."""
+        if not chapters:
+            return False
+        
+        try:
+            from fractions import Fraction
+            from mutagen.mp4 import MP4, MP4Chapter
+        except ImportError:
+            if log_callback:
+                log_callback("Unable to write MP4 chapter atoms because mutagen is not installed.", "warning")
+            return False
+        
+        try:
+            mp4 = MP4(str(audio_path))
+        except Exception as exc:
+            if log_callback:
+                log_callback(f"Failed to open m4b for chapter embedding: {exc}", "warning")
+            return False
+        
+        chapter_objects = []
+        for index, entry in enumerate(sorted(chapters, key=lambda item: float(item.get("start") or 0.0))):
+            start_raw = entry.get("start")
+            if start_raw is None:
+                continue
+            try:
+                start_seconds = max(0.0, float(start_raw))
+            except (TypeError, ValueError):
+                continue
+            
+            title_value = entry.get("title")
+            title_text = str(title_value) if title_value else f"Chapter {index + 1}"
+            
+            start_fraction = Fraction(int(round(start_seconds * 1000)), 1000)
+            chapter_atom = MP4Chapter(start_fraction, title_text)
+            
+            end_raw = entry.get("end")
+            if end_raw is not None:
+                try:
+                    end_seconds = float(end_raw)
+                except (TypeError, ValueError):
+                    end_seconds = None
+                if end_seconds is not None and end_seconds > start_seconds:
+                    chapter_atom.end = Fraction(int(round(end_seconds * 1000)), 1000)
+            
+            chapter_objects.append(chapter_atom)
+        
+        if not chapter_objects:
+            return False
+        
+        try:
+            mp4.chapters = chapter_objects
+            mp4.save()
+        except Exception as exc:
+            if log_callback:
+                log_callback(f"Failed to persist MP4 chapter atoms: {exc}", "warning")
+            return False
+        
+        if log_callback:
+            log_callback(f"Applied {len(chapter_objects)} chapter markers via mutagen", "info")
+        return True
+    
+    # ----------------------------------------------------------------------
+    # EPUB3 Export
+    # ----------------------------------------------------------------------
+    
+    def export_epub3(
+        self,
+        output_path: Path,
+        book_id: str,
+        extraction: Any,  # ExtractionResult
+        metadata_tags: Dict[str, Any],
+        chapter_markers: Sequence[Dict[str, Any]],
+        chunk_markers: Sequence[Dict[str, Any]],
+        chunks: Iterable[Dict[str, Any]],
+        audio_path: Path,
+        speaker_mode: str = "single",
+        cover_path: Optional[Path] = None,
+        cover_mime: Optional[str] = None,
+    ) -> Path:
+        """Export EPUB3 with media overlays."""
+        return build_epub3_package(
+            output_path=output_path,
+            book_id=book_id,
+            extraction=extraction,
+            metadata_tags=metadata_tags,
+            chapter_markers=chapter_markers,
+            chunk_markers=chunk_markers,
+            chunks=chunks,
+            audio_path=audio_path,
+            speaker_mode=speaker_mode,
+            cover_image_path=cover_path,
+            cover_image_mime=cover_mime,
+        )
+    
+    # ----------------------------------------------------------------------
+    # Audiobookshelf Integration
+    # ----------------------------------------------------------------------
+    
+    def build_audiobookshelf_metadata(self, job: Any) -> Dict[str, Any]:
+        """Build Audiobookshelf metadata from job."""
+        filename = Path(getattr(job, "original_filename", "") or "").stem or "Audiobook"
+        return _build_abs_metadata(
+            getattr(job, "metadata_tags", {}),
+            language=getattr(job, "language", "") or "",
+            filename=filename,
+        )
+
+    def load_audiobookshelf_chapters(self, job: Any) -> Optional[List[Dict[str, Any]]]:
+        """Load chapters from job artifacts for Audiobookshelf."""
+        metadata_ref = job.result.artifacts.get("metadata") if getattr(job, "result", None) else None
+        if not metadata_ref:
+            return None
+        metadata_path = metadata_ref if isinstance(metadata_ref, Path) else Path(str(metadata_ref))
+        return _load_abs_chapters(metadata_path)
+    
+    def upload_audiobookshelf(
+        self,
+        job: Any,
+        audio_path: Path,
+        subtitle_paths: List[Path],
+        chapters: List[Dict[str, Any]],
+        metadata: Dict[str, Any],
+        cover_path: Optional[Path] = None,
+        config: Optional[AudiobookshelfConfig] = None,
+        log_callback: Optional[callable] = None,
+    ) -> None:
+        """Upload to Audiobookshelf."""
+        if config is None:
+            cfg = getattr(job, "_abs_config", None)
+            if cfg is None:
+                from abogen.utils import load_config
+                global_cfg = load_config() or {}
+                abs_cfg = global_cfg.get("audiobookshelf")
+                if isinstance(abs_cfg, Mapping):
+                    config = AudiobookshelfConfig(
+                        base_url=str(abs_cfg.get("base_url") or "").strip(),
+                        api_token=str(abs_cfg.get("api_token") or "").strip(),
+                        library_id=str(abs_cfg.get("library_id") or "").strip(),
+                        collection_id=(str(abs_cfg.get("collection_id") or "").strip() or None),
+                        folder_id=str(abs_cfg.get("folder_id") or "").strip(),
+                        verify_ssl=self._coerce_bool(abs_cfg.get("verify_ssl"), True),
+                        send_cover=self._coerce_bool(abs_cfg.get("send_cover"), True),
+                        send_chapters=self._coerce_bool(abs_cfg.get("send_chapters"), True),
+                        send_subtitles=self._coerce_bool(abs_cfg.get("send_subtitles"), False),
+                        timeout=float(abs_cfg.get("timeout", 3600.0)),
+                    )
+                else:
+                    if log_callback:
+                        log_callback("Audiobookshelf upload skipped: not configured", "warning")
+                    return
+
+        if not config.base_url or not config.api_token or not config.library_id:
+            if log_callback:
+                log_callback("Audiobookshelf upload skipped: configure base URL, API token, and library ID first", "warning")
+            return
+        if not config.folder_id:
+            if log_callback:
+                log_callback("Audiobookshelf upload skipped: enter folder name or ID in settings", "warning")
+            return
+
+        if not audio_path.exists():
+            if log_callback:
+                log_callback("Audiobookshelf upload skipped: audio output not found", "warning")
+            return
+        
+        existing_subtitles = [p for p in subtitle_paths if p.exists()] if config.send_subtitles else None
+        chapters_to_send = chapters if config.send_chapters else None
+        
+        client = AudiobookshelfClient(config)
+        
+        display_title = metadata.get("title") or audio_path.stem
+        try:
+            existing_items = client.find_existing_items(display_title, folder_id=config.folder_id)
+        except AudiobookshelfUploadError as exc:
+            if log_callback:
+                log_callback(f"Audiobookshelf lookup failed: {exc}", "error")
+            return
+        
+        if existing_items:
+            if log_callback:
+                log_callback(f"Removing existing Audiobookshelf item(s) for '{display_title}' before upload.", "info")
+            try:
+                client.delete_items(existing_items)
+            except Exception as exc:
+                if log_callback:
+                    log_callback(f"Failed to remove existing item(s): {exc}", "warning")
+        
+        cover_to_send = cover_path
+        if config.send_cover and cover_to_send:
+            if isinstance(cover_to_send, str):
+                cover_to_send = Path(cover_to_send)
+            if not cover_to_send.exists():
+                cover_to_send = None
+        
+        client.upload_audiobook(
+            audio_path,
+            metadata=metadata,
+            cover_path=cover_to_send,
+            chapters=chapters_to_send,
+            subtitles=existing_subtitles,
+        )
+        
+        if log_callback:
+            log_callback("Audiobookshelf upload queued.", "info")
+    
+    # ----------------------------------------------------------------------
+    # Helpers
+    # ----------------------------------------------------------------------
+    
+    @staticmethod
+    def _coerce_bool(value: Any, default: bool = True) -> bool:
+        if isinstance(value, bool):
+            return value
+        if isinstance(value, str):
+            lowered = value.strip().lower()
+            if lowered in {"true", "1", "yes", "on"}:
+                return True
+            if lowered in {"false", "0", "no", "off"}:
+                return False
+            return default
+        if value is None:
+            return default
+        return bool(value)
+
+
+__all__ = [
+    "ExportConfig",
+    "ExportService",
+]

abogen/infrastructure/subtitle_writer.py

@@ -0,0 +1,370 @@
+from __future__ import annotations
+
+from abc import ABC, abstractmethod
+from dataclasses import dataclass
+from enum import Enum
+from pathlib import Path
+from typing import List, Optional, TextIO
+
+from abogen.subtitle_utils import clean_subtitle_text
+
+
+class SubtitleFormat(Enum):
+    SRT = "srt"
+    ASS = "ass"
+    VTT = "vtt"
+
+
+class SubtitleMode(Enum):
+    DISABLED = "Disabled"
+    LINE = "Line"
+    SENTENCE = "Sentence"
+    SENTENCE_COMMA = "Sentence + Comma"
+    SENTENCE_HIGHLIGHT = "Sentence + Highlighting"
+
+
+class SubtitleAlignment(Enum):
+    LEFT = "left"
+    CENTER = "center"
+    NARROW = "narrow"
+    CENTER_NARROW = "center_narrow"
+
+
+@dataclass
+class SubtitleConfig:
+    """Configuration for subtitle writer."""
+    format: SubtitleFormat
+    mode: SubtitleMode
+    alignment: SubtitleAlignment = SubtitleAlignment.LEFT
+    max_words: int = 50
+    highlight_color: str = "&H00FFFF00"  # ASS highlight color
+
+
+class SubtitleWriter(ABC):
+    """Abstract base class for subtitle writers."""
+    
+    def __init__(self, path: Path, config: SubtitleConfig):
+        self.path = path
+        self.config = config
+        self._file: Optional[TextIO] = None
+        self._index = 0
+        self._opened = False
+    
+    def open(self) -> None:
+        """Open the subtitle file and write header."""
+        if self._opened:
+            return
+        self._file = open(self.path, "w", encoding="utf-8", errors="replace")
+        self._write_header()
+        self._opened = True
+    
+    @abstractmethod
+    def _write_header(self) -> None:
+        pass
+    
+    def write_entry(
+        self,
+        start: float,
+        end: float,
+        text: str,
+        voice: Optional[str] = None,
+    ) -> None:
+        """Write a subtitle entry."""
+        if not self._opened:
+            self.open()
+        
+        text = clean_subtitle_text(text)
+        if not text:
+            return
+        
+        self._index += 1
+        self._write_entry(self._index, start, end, text, voice)
+    
+    @abstractmethod
+    def _write_entry(
+        self,
+        index: int,
+        start: float,
+        end: float,
+        text: str,
+        voice: Optional[str],
+    ) -> None:
+        pass
+    
+    def close(self) -> None:
+        """Close the subtitle file."""
+        if self._file:
+            self._file.close()
+            self._file = None
+            self._opened = False
+    
+    def __enter__(self) -> "SubtitleWriter":
+        self.open()
+        return self
+    
+    def __exit__(self, exc_type, exc_val, exc_tb) -> None:
+        self.close()
+
+
+class SrtWriter(SubtitleWriter):
+    """SRT subtitle writer."""
+    
+    def _write_header(self) -> None:
+        pass  # SRT has no header
+    
+    def _write_entry(
+        self,
+        index: int,
+        start: float,
+        end: float,
+        text: str,
+        voice: Optional[str],
+    ) -> None:
+        start_str = self._format_time(start)
+        end_str = self._format_time(end)
+        
+        if voice:
+            text = f"[{voice}] {text}"
+        
+        self._file.write(f"{index}\n")
+        self._file.write(f"{start_str} --> {end_str}\n")
+        self._file.write(f"{text}\n\n")
+    
+    @staticmethod
+    def _format_time(seconds: float) -> str:
+        hours = int(seconds // 3600)
+        minutes = int((seconds % 3600) // 60)
+        secs = int(seconds % 60)
+        millis = int((seconds - int(seconds)) * 1000)
+        return f"{hours:02d}:{minutes:02d}:{secs:02d},{millis:03d}"
+
+
+class VttWriter(SubtitleWriter):
+    """WebVTT subtitle writer."""
+    
+    def _write_header(self) -> None:
+        self._file.write("WEBVTT\n\n")
+    
+    def _write_entry(
+        self,
+        index: int,
+        start: float,
+        end: float,
+        text: str,
+        voice: Optional[str],
+    ) -> None:
+        start_str = self._format_time(start)
+        end_str = self._format_time(end)
+        
+        if voice:
+            text = f"[{voice}] {text}"
+        
+        self._file.write(f"{index}\n")
+        self._file.write(f"{start_str} --> {end_str}\n")
+        self._file.write(f"{text}\n\n")
+    
+    @staticmethod
+    def _format_time(seconds: float) -> str:
+        hours = int(seconds // 3600)
+        minutes = int((seconds % 3600) // 60)
+        secs = seconds % 60
+        return f"{hours:02d}:{minutes:02d}:{secs:06.3f}".replace(".", ".")
+
+
+class AssWriter(SubtitleWriter):
+    """ASS subtitle writer with karaoke highlighting support."""
+    
+    def __init__(self, path: Path, config: SubtitleConfig):
+        super().__init__(path, config)
+        self._is_centered = config.alignment in (SubtitleAlignment.CENTER, SubtitleAlignment.CENTER_NARROW)
+        self._is_narrow = config.alignment in (SubtitleAlignment.NARROW, SubtitleAlignment.CENTER_NARROW)
+    
+    def _write_header(self) -> None:
+        margin = "90" if self._is_narrow else "10"
+        alignment = "5" if self._is_centered else "2"
+        
+        self._file.write("[Script Info]\n")
+        self._file.write("Title: Generated by Abogen\n")
+        self._file.write("ScriptType: v4.00+\n\n")
+        
+        # Styles
+        self._file.write("[V4+ Styles]\n")
+        self._file.write(
+            "Format: Name, Fontname, Fontsize, PrimaryColour, SecondaryColour, "
+            "OutlineColour, BackColour, Bold, Italic, Underline, StrikeOut, "
+            "ScaleX, ScaleY, Spacing, Angle, BorderStyle, Outline, Shadow, "
+            "Alignment, MarginL, MarginR, MarginV, Encoding\n"
+        )
+        
+        if self.config.mode == SubtitleMode.SENTENCE_HIGHLIGHT:
+            # Karaoke style with highlighting
+            self._file.write(
+                f"Style: Default,Arial,24,&H00FFFFFF,&H00808080,&H00000000,&H00404040,"
+                f"0,0,0,0,100,100,0,0,3,2,0,{alignment},{margin},{margin},10,1\n"
+            )
+            self._file.write(
+                f"Style: Highlight,Arial,24,&H0000FFFF,&H00808080,&H00000000,&H00404040,"
+                f"0,0,0,0,100,100,0,0,3,2,0,{alignment},{margin},{margin},10,1\n\n"
+            )
+        else:
+            self._file.write(
+                f"Style: Default,Arial,24,&H00FFFFFF,&H00808080,&H00000000,&H00404040,"
+                f"0,0,0,0,100,100,0,0,3,2,0,{alignment},{margin},{margin},10,1\n\n"
+            )
+        
+        self._file.write("[Events]\n")
+        self._file.write(
+            "Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text\n"
+        )
+    
+    def _write_entry(
+        self,
+        index: int,
+        start: float,
+        end: float,
+        text: str,
+        voice: Optional[str],
+    ) -> None:
+        start_str = self._format_time(start)
+        end_str = self._format_time(end)
+        
+        if voice:
+            text = f"[{voice}] {text}"
+        
+        style = "Default"
+        if self.config.mode == SubtitleMode.SENTENCE_HIGHLIGHT:
+            # Add karaoke tags for highlighting
+            text = self._add_karaoke_tags(text)
+            style = "Highlight"
+        
+        alignment_tag = r"{\an5}" if self._is_centered else ""
+        self._file.write(
+            f"Dialogue: 0,{start_str},{end_str},{style},,0,0,0,,{alignment_tag}{text}\n"
+        )
+    
+    def _add_karaoke_tags(self, text: str) -> str:
+        """Add karaoke highlighting tags to text."""
+        # Simple word-level karaoke timing
+        words = text.split()
+        if not words:
+            return text
+        
+        # This is a simplified version - real karaoke needs per-word timing
+        # For now, just return the text with the highlight color
+        return r"{\k100}" + r"{\k100}".join(words) + r"{\k0}"
+    
+    @staticmethod
+    def _format_time(seconds: float) -> str:
+        hours = int(seconds // 3600)
+        minutes = int((seconds % 3600) // 60)
+        secs = seconds % 60
+        return f"{hours}:{minutes:02d}:{secs:05.2f}"
+
+
+def create_subtitle_writer(
+    path: Path,
+    format: str,
+    mode: str,
+    alignment: str = "left",
+    max_words: int = 50,
+) -> SubtitleWriter:
+    """Factory function to create subtitle writer."""
+    fmt = SubtitleFormat(format.lower())
+    mode = SubtitleMode(mode)
+    align = SubtitleAlignment(alignment.lower())
+
+    config = SubtitleConfig(
+        format=fmt,
+        mode=mode,
+        alignment=align,
+        max_words=max_words,
+    )
+
+    if fmt == SubtitleFormat.SRT:
+        return SrtWriter(path, config)
+    elif fmt == SubtitleFormat.VTT:
+        return VttWriter(path, config)
+    elif fmt == SubtitleFormat.ASS:
+        return AssWriter(path, config)
+    else:
+        raise ValueError(f"Unsupported subtitle format: {format}")
+
+
+def resolve_subtitle_format(
+    subtitle_format: str | None,
+    subtitle_mode: str,
+) -> tuple[str, str]:
+    """Resolve a subtitle_format setting string to (file_extension, alignment).
+
+    Handles the PyQt convention where format strings encode alignment
+    (e.g. ``"ass_centered_narrow"`` → extension ``"ass"``, alignment
+    ``"center_narrow"``).
+
+    Also enforces that ``"Sentence + Highlighting"`` mode requires ASS.
+
+    Returns:
+        Tuple of (file_extension, alignment) suitable for
+        :func:`create_subtitle_writer`.
+    """
+    fmt = (subtitle_format or "srt").lower()
+
+    if subtitle_mode == "Sentence + Highlighting" and fmt == "srt":
+        fmt = "ass"
+
+    if "ass" in fmt:
+        extension = "ass"
+        if "centered_narrow" in fmt:
+            alignment = "center_narrow"
+        elif "centered" in fmt:
+            alignment = "center"
+        elif "narrow" in fmt:
+            alignment = "narrow"
+        else:
+            alignment = "left"
+    else:
+        extension = fmt if fmt in ("srt", "vtt") else "srt"
+        alignment = "left"
+
+    return extension, alignment
+
+
+def make_subtitle_writer(
+    audio_path: Path,
+    subtitle_format: str | None,
+    subtitle_mode: str,
+    max_words: int = 50,
+) -> SubtitleWriter | None:
+    """Convenience: resolve format and create a writer, or return None if disabled.
+
+    Returns ``None`` when ``subtitle_mode`` is ``"Disabled"`` or the
+    format is unsupported.
+    """
+    if subtitle_mode == "Disabled":
+        return None
+
+    extension, alignment = resolve_subtitle_format(subtitle_format, subtitle_mode)
+    try:
+        return create_subtitle_writer(
+            audio_path.with_suffix(f".{extension}"),
+            extension,
+            subtitle_mode,
+            alignment=alignment,
+            max_words=max_words,
+        )
+    except (ValueError, KeyError):
+        return None
+
+
+__all__ = [
+    "SubtitleFormat",
+    "SubtitleMode",
+    "SubtitleAlignment",
+    "SubtitleConfig",
+    "SubtitleWriter",
+    "SrtWriter",
+    "VttWriter",
+    "AssWriter",
+    "create_subtitle_writer",
+    "resolve_subtitle_format",
+    "make_subtitle_writer",
+]

abogen/integrations/audiobookshelf.py

@@ -2,9 +2,7 @@ from __future__ import annotations
 
 import json
 import logging
-import math
 import mimetypes
-import re
 from contextlib import ExitStack
 from dataclasses import dataclass
 from pathlib import Path
@@ -12,6 +10,8 @@ from typing import Any, Dict, Iterable, List, Mapping, Optional, Sequence, Tuple
 
 import httpx
 
+from abogen.domain.metadata_helpers import normalize_series_sequence
+
 logger = logging.getLogger(__name__)
 
 
@@ -641,40 +641,7 @@ class AudiobookshelfClient:
         for key in preferred_keys:
             if key not in metadata:
                 continue
-            normalized = AudiobookshelfClient._normalize_series_sequence(metadata.get(key))
+            normalized = normalize_series_sequence(metadata.get(key))
             if normalized:
                 return normalized
         return ""
-
-    @staticmethod
-    def _normalize_series_sequence(raw: Any) -> str:
-        if raw is None:
-            return ""
-
-        if isinstance(raw, (int, float)):
-            if isinstance(raw, float) and (math.isnan(raw) or math.isinf(raw)):
-                return ""
-            text = str(raw)
-        else:
-            text = str(raw).strip()
-
-        if not text:
-            return ""
-
-        candidate = text.replace(",", ".")
-        match = re.search(r"\d+(?:\.\d+)?", candidate)
-        if not match:
-            return ""
-
-        normalized = match.group(0)
-        if "." in normalized:
-            normalized = normalized.rstrip("0").rstrip(".")
-            if not normalized:
-                normalized = "0"
-            return normalized
-
-        try:
-            return str(int(normalized))
-        except ValueError:
-            cleaned = normalized.lstrip("0")
-            return cleaned or "0"

abogen/main.py

@@ -2,13 +2,14 @@
 
 from __future__ import annotations
 
-import atexit
 import os
 import platform
-import signal
-import sys
 
-from abogen.utils import load_config, prevent_sleep_end
+# Initialise global shutdown handling (atexit, signals, Qt) as early as possible.
+from abogen import shutdown  # noqa: F401
+shutdown.register_shutdown()
+
+from abogen.utils import load_config
 from abogen.webui.app import main as _run_web_ui
 
 # Configure Hugging Face Hub behaviour (mirrors legacy GUI defaults).
@@ -27,17 +28,6 @@ os.environ.setdefault("MIOPEN_CONV_PRECISE_ROCM_TUNING", "0")
 if platform.system() == "Darwin" and platform.processor() == "arm":
     os.environ.setdefault("PYTORCH_ENABLE_MPS_FALLBACK", "1")
 
-atexit.register(prevent_sleep_end)
-
-
-def _cleanup_sleep(signum, _frame):
-    prevent_sleep_end()
-    sys.exit(0)
-
-
-signal.signal(signal.SIGINT, _cleanup_sleep)
-signal.signal(signal.SIGTERM, _cleanup_sleep)
-
 
 def main() -> None:
     """Launch the Flask-based web UI."""

abogen/predownload_gui.py

@@ -21,7 +21,8 @@ from PyQt6.QtWidgets import (
 )
 from PyQt6.QtCore import QThread, pyqtSignal
 
-from abogen.constants import COLORS, VOICES_INTERNAL
+from abogen.constants import COLORS
+from abogen.tts_plugin.utils import get_voices
 from abogen.spacy_utils import SPACY_MODELS
 import abogen.hf_tracker
 
@@ -114,7 +115,7 @@ class PreDownloadWorker(QThread):
             self._voices_success = False
             return
 
-        voice_list = VOICES_INTERNAL
+        voice_list = get_voices("kokoro")
         for idx, voice in enumerate(voice_list, start=1):
             if self._cancelled:
                 self._voices_success = False
@@ -462,14 +463,14 @@ class PreDownloadDialog(QDialog):
         try:
             from huggingface_hub import try_to_load_from_cache
 
-            for voice in VOICES_INTERNAL:
+            for voice in get_voices("kokoro"):
                 if not try_to_load_from_cache(
                     repo_id="hexgrad/Kokoro-82M", filename=f"voices/{voice}.pt"
                 ):
                     missing.append(voice)
         except Exception:
             # If HF missing, report all as missing
-            return False, list(VOICES_INTERNAL)
+            return False, list(get_voices("kokoro"))
         return (len(missing) == 0), missing
 
     def _check_kokoro_model(self) -> bool:

abogen/pyqt/book_handler.py

@@ -29,6 +29,12 @@ from abogen.utils import (
     get_resource_path,
 )
 from abogen.book_parser import get_book_parser
+from abogen.domain.metadata_extraction import (
+    extract_book_metadata_epub,
+    extract_book_metadata_pdf,
+    extract_book_metadata_markdown,
+    format_metadata_tags,
+)
 
 from abogen.subtitle_utils import (
     clean_text,
@@ -948,169 +954,14 @@ class HandlerDialog(QDialog):
         self.previewEdit.setHtml(html_content)
 
     def _extract_book_metadata(self):
-        metadata = {
-            "title": None,
-            "authors": [],
-            "description": None,
-            "cover_image": None,
-            "publisher": None,
-            "publication_year": None,
-        }
-
         if self.parser.file_type == "epub":
-            try:
+            return extract_book_metadata_epub(self.book)
-                title_items = self.book.get_metadata("DC", "title")
-                if title_items and len(title_items) > 0:
-                    metadata["title"] = title_items[0][0]
-            except Exception as e:
-                logging.warning(f"Error extracting title metadata: {e}")
-
-            try:
-                author_items = self.book.get_metadata("DC", "creator")
-                if author_items:
-                    metadata["authors"] = [
-                        author[0] for author in author_items if len(author) > 0
-                    ]
-            except Exception as e:
-                logging.warning(f"Error extracting author metadata: {e}")
-
-            try:
-                desc_items = self.book.get_metadata("DC", "description")
-                if desc_items and len(desc_items) > 0:
-                    metadata["description"] = desc_items[0][0]
-            except Exception as e:
-                logging.warning(f"Error extracting description metadata: {e}")
-
-            try:
-                publisher_items = self.book.get_metadata("DC", "publisher")
-                if publisher_items and len(publisher_items) > 0:
-                    metadata["publisher"] = publisher_items[0][0]
-            except Exception as e:
-                logging.warning(f"Error extracting publisher metadata: {e}")
-
-            # Try to extract publication year
-            try:
-                date_items = self.book.get_metadata("DC", "date")
-                if date_items and len(date_items) > 0:
-                    date_str = date_items[0][0]
-                    # Try to extract just the year from the date string
-                    year_match = re.search(r"\b(19|20)\d{2}\b", date_str)
-                    if year_match:
-                        metadata["publication_year"] = year_match.group(0)
-                    else:
-                        metadata["publication_year"] = date_str
-            except Exception as e:
-                logging.warning(f"Error extracting publication date metadata: {e}")
-
-            for item in self.book.get_items_of_type(ebooklib.ITEM_COVER):
-                metadata["cover_image"] = item.get_content()
-                break
-
-            if not metadata["cover_image"]:
-                for item in self.book.get_items_of_type(ebooklib.ITEM_IMAGE):
-                    if "cover" in item.get_name().lower():
-                        metadata["cover_image"] = item.get_content()
-                        break
         elif self.parser.file_type == "markdown":
-            # Extract metadata from markdown frontmatter or first heading
+            return extract_book_metadata_markdown(
-            if self.markdown_text:
+                self.markdown_text, self.markdown_toc
-                # Try to extract YAML frontmatter
-                frontmatter_match = re.match(
-                    r"^---\s*\n(.*?)\n---\s*\n", self.markdown_text, re.DOTALL
             )
-                if frontmatter_match:
-                    try:
-                        frontmatter = frontmatter_match.group(1)
-                        # Simple YAML-like parsing for common fields
-                        title_match = re.search(
-                            r"^title:\s*(.+)$",
-                            frontmatter,
-                            re.MULTILINE | re.IGNORECASE,
-                        )
-                        if title_match:
-                            metadata["title"] = (
-                                title_match.group(1).strip().strip("\"'")
-                            )
-
-                        author_match = re.search(
-                            r"^author:\s*(.+)$",
-                            frontmatter,
-                            re.MULTILINE | re.IGNORECASE,
-                        )
-                        if author_match:
-                            metadata["authors"] = [
-                                author_match.group(1).strip().strip("\"'")
-                            ]
-
-                        desc_match = re.search(
-                            r"^description:\s*(.+)$",
-                            frontmatter,
-                            re.MULTILINE | re.IGNORECASE,
-                        )
-                        if desc_match:
-                            metadata["description"] = (
-                                desc_match.group(1).strip().strip("\"'")
-                            )
-
-                        date_match = re.search(
-                            r"^date:\s*(.+)$", frontmatter, re.MULTILINE | re.IGNORECASE
-                        )
-                        if date_match:
-                            date_str = date_match.group(1).strip().strip("\"'")
-                            year_match = re.search(r"\b(19|20)\d{2}\b", date_str)
-                            if year_match:
-                                metadata["publication_year"] = year_match.group(0)
-                    except Exception as e:
-                        logging.warning(f"Error parsing markdown frontmatter: {e}")
-
-                # Fallback: use first H1 header as title if no frontmatter title
-                if not metadata["title"] and self.markdown_toc:
-                    # Find the first level 1 header
-                    first_h1 = next(
-                        (h for h in self.markdown_toc if h["level"] == 1), None
-                    )
-                    if first_h1:
-                        metadata["title"] = first_h1["name"]
         else:
-            pdf_info = self.pdf_doc.metadata
+            return extract_book_metadata_pdf(self.pdf_doc)
-            if pdf_info:
-                metadata["title"] = pdf_info.get("title", None)
-
-                author = pdf_info.get("author", None)
-                if author:
-                    metadata["authors"] = [author]
-
-                metadata["description"] = pdf_info.get("subject", None)
-
-                keywords = pdf_info.get("keywords", None)
-                if keywords:
-                    if metadata["description"]:
-                        metadata["description"] += f"\n\nKeywords: {keywords}"
-                    else:
-                        metadata["description"] = f"Keywords: {keywords}"
-
-                metadata["publisher"] = pdf_info.get("creator", None)
-
-                # Try to extract publication date from PDF metadata
-                if "creationDate" in pdf_info:
-                    date_str = pdf_info["creationDate"]
-                    year_match = re.search(r"D:(\d{4})", date_str)
-                    if year_match:
-                        metadata["publication_year"] = year_match.group(1)
-                elif "modDate" in pdf_info:
-                    date_str = pdf_info["modDate"]
-                    year_match = re.search(r"D:(\d{4})", date_str)
-                    if year_match:
-                        metadata["publication_year"] = year_match.group(1)
-
-            if len(self.pdf_doc) > 0:
-                try:
-                    pix = self.pdf_doc[0].get_pixmap(matrix=fitz.Matrix(2, 2))
-                    metadata["cover_image"] = pix.tobytes("png")
-                except Exception:
-                    pass
-
-        return metadata
 
     def get_selected_text(self):
         # If a background loader thread is running, wait for it to finish to
@@ -1136,58 +987,20 @@ class HandlerDialog(QDialog):
 
     def _format_metadata_tags(self):
         """Format metadata tags for insertion at the beginning of the text"""
-        import datetime
         from abogen.utils import get_user_cache_path
 
-        metadata = self.book_metadata
         filename = os.path.splitext(os.path.basename(self.book_path))[0]
-        current_year = str(datetime.datetime.now().year)
+        chapter_count = len(self.checked_chapters)
-
-        # Get values with fallbacks
-        title = metadata.get("title") or filename
-        authors = metadata.get("authors") or ["Unknown"]
-        authors_text = ", ".join(authors)
-        album_artist = authors_text or "Unknown"
-        year = (
-            metadata.get("publication_year") or current_year
-        )  # Use publication year if available
-
-        # Count chapters/pages
-        total_chapters = len(self.checked_chapters)
-        chapter_text = (
-            f"{total_chapters} {'Chapters' if self.parser.file_type == 'epub' else 'Pages'}"
-        )
-
-        # Handle cover image
-        cover_tag = ""
-        if metadata.get("cover_image"):
-            try:
-                import uuid
-
         cache_dir = get_user_cache_path()
-                cover_path = os.path.join(cache_dir, f"cover_{uuid.uuid4()}.jpg")
-                cover_path = os.path.normpath(cover_path)
-                with open(cover_path, "wb") as f:
-                    f.write(metadata["cover_image"])
-                cover_tag = f"<<METADATA_COVER_PATH:{cover_path}>>"
-            except Exception as e:
-                logging.warning(f"Failed to save cover image: {e}")
 
-        # Format metadata tags
+        return format_metadata_tags(
-        metadata_tags = [
+            self.book_metadata,
-            f"<<METADATA_TITLE:{title}>>",
+            filename,
-            f"<<METADATA_ARTIST:{authors_text}>>",
+            chapter_count,
-            f"<<METADATA_ALBUM:{title} ({chapter_text})>>",
+            self.parser.file_type,
-            f"<<METADATA_YEAR:{year}>>",
+            cover_bytes=self.book_metadata.get("cover_image"),
-            f"<<METADATA_ALBUM_ARTIST:{album_artist}>>",
+            cache_dir=cache_dir,
-            f"<<METADATA_COMPOSER:Narrator>>",
+        )
-            f"<<METADATA_GENRE:Audiobook>>",
-        ]
-
-        if cover_tag:
-            metadata_tags.append(cover_tag)
-
-        return "\n".join(metadata_tags)
 
     def _get_markdown_selected_text(self):
         """Get selected text from markdown chapters"""

abogen/pyqt/gui.py

@@ -7,6 +7,7 @@ import base64
 import re
 from abogen.pyqt.queue_manager_gui import QueueManager
 from abogen.pyqt.queued_item import QueuedItem
+
 import abogen.hf_tracker as hf_tracker
 import hashlib  # Added for cache path generation
 from PyQt6.QtWidgets import (
@@ -74,7 +75,7 @@ from abogen.subtitle_utils import (
     calculate_text_length,
 )
 
-from abogen.conversion import ConversionThread, VoicePreviewThread, PlayAudioThread
+from abogen.pyqt.conversion import ConversionThread, VoicePreviewThread, PlayAudioThread, ChapterOptionsDialog, TimestampDetectionDialog
 from abogen.pyqt.book_handler import HandlerDialog
 from abogen.constants import (
     PROGRAM_NAME,
@@ -82,14 +83,18 @@ from abogen.constants import (
     GITHUB_URL,
     PROGRAM_DESCRIPTION,
     LANGUAGE_DESCRIPTIONS,
-    VOICES_INTERNAL,
     SUPPORTED_LANGUAGES_FOR_SUBTITLE_GENERATION,
     COLORS,
     SUBTITLE_FORMATS,
 )
+from abogen.tts_plugin.utils import get_voices
 import threading
 from abogen.pyqt.voice_formula_gui import VoiceFormulaDialog
 from abogen.voice_profiles import load_profiles
+from abogen.domain.settings_core import all_settings_defaults
+
+# Module-level default cache for use outside __init__
+_DEFAULTS = all_settings_defaults()
 
 # Import ctypes for Windows-specific taskbar icon
 if platform.system() == "Windows":
@@ -665,6 +670,11 @@ class TextboxDialog(QDialog):
         self.insert_chapter_btn.clicked.connect(self.insert_chapter_marker)
         button_layout.addWidget(self.insert_chapter_btn)
 
+        self.insert_voice_btn = QPushButton("Insert Voice Marker", self)
+        self.insert_voice_btn.setToolTip("Insert a voice change marker at the cursor position")
+        self.insert_voice_btn.clicked.connect(self.insert_voice_marker)
+        button_layout.addWidget(self.insert_voice_btn)
+
         self.cancel_button = QPushButton("Cancel", self)
         self.cancel_button.clicked.connect(self.reject)
 
@@ -767,6 +777,23 @@ class TextboxDialog(QDialog):
         self.update_char_count()
         self.text_edit.setFocus()
 
+    def insert_voice_marker(self):
+        """Insert a voice marker template at cursor position."""
+        cursor = self.text_edit.textCursor()
+        # Use the currently selected voice as the default
+        try:
+            parent_window = self.parent()
+            if parent_window and hasattr(parent_window, 'selected_voice'):
+                default_voice = parent_window.selected_voice or "af_heart"
+            else:
+                default_voice = "af_heart"
+        except Exception:
+            default_voice = "af_heart"
+        cursor.insertText(f"\n<<VOICE:{default_voice}>>\n")
+        self.text_edit.setTextCursor(cursor)
+        self.update_char_count()
+        self.text_edit.setFocus()
+
 
 def migrate_subtitle_format(config):
     """Convert old subtitle_format values to new internal keys."""
@@ -783,13 +810,116 @@ def migrate_subtitle_format(config):
         save_config(config)
 
 
+class WordSubstitutionsDialog(QDialog):
+    """Dialog for configuring word substitutions and text preprocessing options."""
+
+    def __init__(
+        self,
+        parent=None,
+        initial_list="",
+        initial_case_sensitive=False,
+        initial_caps=False,
+        initial_numerals=False,
+        initial_punctuation=False,
+    ):
+        super().__init__(parent)
+        self.setWindowTitle("Word Substitutions Settings")
+        self.setWindowFlags(
+            Qt.WindowType.Window
+            | Qt.WindowType.WindowCloseButtonHint
+            | Qt.WindowType.WindowMaximizeButtonHint
+        )
+        self.resize(600, 500)
+
+        layout = QVBoxLayout(self)
+
+        # Instructions
+        instructions = QLabel(
+            "Enter word substitutions (one per line) in format: Word|NewWord\n"
+            "  - If nothing after |, the word will be erased completely\n"
+            "  - Substitutions match whole words only (e.g., \"tree\" won't match \"trees\" but will match \"tree's\")\n"
+            "  - By default, matching is case-insensitive (e.g., \"gonna\" matches \"Gonna\", \"GONNA\", etc.)",
+            self,
+        )
+        instructions.setStyleSheet(
+            "padding: 10px; background-color: #f0f0f0; border-radius: 5px;"
+        )
+        instructions.setWordWrap(True)
+        layout.addWidget(instructions)
+
+        # Text edit area
+        self.text_edit = QTextEdit(self)
+        self.text_edit.setAcceptRichText(False)
+        self.text_edit.setPlaceholderText("Word|NewWord")
+        self.text_edit.setPlainText(initial_list)
+        layout.addWidget(self.text_edit)
+
+        # Checkboxes
+        self.case_sensitive_checkbox = QCheckBox(
+            "Case-sensitive word matching", self
+        )
+        self.case_sensitive_checkbox.setChecked(initial_case_sensitive)
+        layout.addWidget(self.case_sensitive_checkbox)
+
+        self.caps_checkbox = QCheckBox("Replace ALL CAPS with lowercase", self)
+        self.caps_checkbox.setChecked(initial_caps)
+        layout.addWidget(self.caps_checkbox)
+
+        self.numerals_checkbox = QCheckBox(
+            "Replace Numerals with Words (e.g., 309 \u2192 three hundred and nine)", self
+        )
+        self.numerals_checkbox.setChecked(initial_numerals)
+        layout.addWidget(self.numerals_checkbox)
+
+        self.punctuation_checkbox = QCheckBox(
+            "Fix Nonstandard Punctuation (curly quotes and other Unicode punctuation that may affect how words sound)",
+            self,
+        )
+        self.punctuation_checkbox.setChecked(initial_punctuation)
+        layout.addWidget(self.punctuation_checkbox)
+
+        # Buttons
+        button_layout = QHBoxLayout()
+        self.cancel_button = QPushButton("Cancel", self)
+        self.cancel_button.clicked.connect(self.reject)
+        self.ok_button = QPushButton("OK", self)
+        self.ok_button.setDefault(True)
+        self.ok_button.clicked.connect(self.accept)
+
+        button_layout.addStretch()
+        button_layout.addWidget(self.cancel_button)
+        button_layout.addWidget(self.ok_button)
+        layout.addLayout(button_layout)
+
+    def get_substitutions_list(self):
+        """Get the substitutions list as plain text."""
+        return self.text_edit.toPlainText()
+
+    def get_case_sensitive(self):
+        """Get whether case-sensitive matching is enabled."""
+        return self.case_sensitive_checkbox.isChecked()
+
+    def get_replace_all_caps(self):
+        """Get whether ALL CAPS replacement is enabled."""
+        return self.caps_checkbox.isChecked()
+
+    def get_replace_numerals(self):
+        """Get whether numeral-to-word conversion is enabled."""
+        return self.numerals_checkbox.isChecked()
+
+    def get_fix_nonstandard_punctuation(self):
+        """Get whether nonstandard punctuation fixing is enabled."""
+        return self.punctuation_checkbox.isChecked()
+
+
 class abogen(QWidget):
     def __init__(self):
         super().__init__()
         self.config = load_config()
-        self.apply_theme(self.config.get("theme", "system"))
+        _d = all_settings_defaults()
+        self.apply_theme(self.config.get("theme", _d["theme"]))
         migrate_subtitle_format(self.config)
-        self.check_updates = self.config.get("check_updates", True)
+        self.check_updates = self.config.get("check_updates", _d["check_updates"])
         self.save_option = self.config.get("save_option", "Save next to input file")
         self.selected_output_folder = self.config.get("selected_output_folder", None)
         self.selected_file = self.selected_file_type = self.selected_book_path = None
@@ -797,7 +927,7 @@ class abogen(QWidget):
             None  # Add new variable to track the displayed file path
         )
         # Max log lines
-        self.log_window_max_lines = self.config.get("log_window_max_lines", 2000)
+        self.log_window_max_lines = self.config.get("log_window_max_lines", _d["log_window_max_lines"])
         self.selected_chapters = set()
         self.last_opened_book_path = None  # Track the last opened book path
         self.last_output_path = None
@@ -812,27 +942,28 @@ class abogen(QWidget):
             self.selected_voice = None
             self.selected_lang = None
         else:
-            self.selected_voice = self.config.get("selected_voice", "af_heart")
+            self.selected_voice = self.config.get("selected_voice", _d["selected_voice"])
             self.selected_lang = self.selected_voice[0] if self.selected_voice else None
         self.is_converting = False
-        self.subtitle_mode = self.config.get("subtitle_mode", "Sentence")
+        self.subtitle_mode = self.config.get("subtitle_mode", _d["subtitle_mode"])
-        self.max_subtitle_words = self.config.get(
+        self.max_subtitle_words = self.config.get("max_subtitle_words", _d["max_subtitle_words"])
-            "max_subtitle_words", 50
+        self.silence_duration = self.config.get("silence_duration", _d.get("silence_between_chapters", 2.0))
-        )  # Default max words per subtitle
+        self.selected_format = self.config.get("selected_format", _d["selected_format"])
-        self.silence_duration = self.config.get(
+        self.separate_chapters_format = self.config.get("separate_chapters_format", _d["separate_chapters_format"])
-            "silence_duration", 2.0
+        self.use_gpu = self.config.get("use_gpu", _d["use_gpu"])
-        )  # Default silence duration
+        self.replace_single_newlines = self.config.get("replace_single_newlines", _d.get("replace_single_newlines", True))
-        self.selected_format = self.config.get("selected_format", "wav")
+        self.use_silent_gaps = self.config.get("use_silent_gaps", _d["use_silent_gaps"])
-        self.separate_chapters_format = self.config.get(
+        self.subtitle_speed_method = self.config.get("subtitle_speed_method", _d["subtitle_speed_method"])
-            "separate_chapters_format", "wav"
+        self.use_spacy_segmentation = self.config.get("use_spacy_segmentation", _d["use_spacy_segmentation"])
-        )  # Format for individual chapter files
+        self.read_title_intro = self.config.get("read_title_intro", _d.get("read_title_intro", False))
-        self.use_gpu = self.config.get(
+        self.read_closing_outro = self.config.get("read_closing_outro", _d.get("read_closing_outro", True))
-            "use_gpu", True  # Load GPU setting with default True
+        # Word substitution settings
-        )
+        self.word_substitutions_enabled = self.config.get("word_substitutions_enabled", _d["word_substitutions_enabled"])
-        self.replace_single_newlines = self.config.get("replace_single_newlines", True)
+        self.word_substitutions_list = self.config.get("word_substitutions_list", _d["word_substitutions_list"])
-        self.use_silent_gaps = self.config.get("use_silent_gaps", True)
+        self.case_sensitive_substitutions = self.config.get("case_sensitive_substitutions", _d["case_sensitive_substitutions"])
-        self.subtitle_speed_method = self.config.get("subtitle_speed_method", "tts")
+        self.replace_all_caps = self.config.get("replace_all_caps", _d["replace_all_caps"])
-        self.use_spacy_segmentation = self.config.get("use_spacy_segmentation", True)
+        self.replace_numerals = self.config.get("replace_numerals", _d["replace_numerals"])
+        self.fix_nonstandard_punctuation = self.config.get("fix_nonstandard_punctuation", _d["fix_nonstandard_punctuation"])
         self._pending_close_event = None
         self.gpu_ok = False  # Initialize GPU availability status
 
@@ -860,7 +991,7 @@ class abogen(QWidget):
         self.current_queue_index = 0
 
         self.initUI()
-        self.speed_slider.setValue(int(self.config.get("speed", 1.00) * 100))
+        self.speed_slider.setValue(int(self.config.get("speed", _d["speed"]) * 100))
         self.update_speed_label()
         # Set initial selection: prefer profile, else voice
         idx = -1
@@ -1071,6 +1202,35 @@ class abogen(QWidget):
         subtitle_layout.addWidget(self.subtitle_combo)
         controls_layout.addLayout(subtitle_layout)
 
+        # Word Substitutions section
+        word_sub_layout = QHBoxLayout()
+        word_sub_layout.setSpacing(7)
+        word_sub_label = QLabel("Word Substitutions:", self)
+        word_sub_layout.addWidget(word_sub_label)
+
+        self.word_sub_combo = QComboBox(self)
+        self.word_sub_combo.addItems(["Disabled", "Enabled"])
+        self.word_sub_combo.setStyleSheet(
+            "QComboBox { min-height: 20px; padding: 6px 12px; }"
+        )
+        self.word_sub_combo.setSizePolicy(
+            QSizePolicy.Policy.Expanding, QSizePolicy.Policy.Fixed
+        )
+        self.word_sub_combo.setCurrentText(
+            "Enabled" if self.word_substitutions_enabled else "Disabled"
+        )
+        self.word_sub_combo.currentTextChanged.connect(self.on_word_sub_changed)
+        word_sub_layout.addWidget(self.word_sub_combo)
+
+        self.btn_word_sub_settings = QPushButton("Settings", self)
+        self.btn_word_sub_settings.setFixedSize(80, 36)
+        self.btn_word_sub_settings.setStyleSheet("QPushButton { padding: 6px 12px; }")
+        self.btn_word_sub_settings.clicked.connect(self.show_word_sub_dialog)
+        self.btn_word_sub_settings.setEnabled(self.word_substitutions_enabled)
+        word_sub_layout.addWidget(self.btn_word_sub_settings)
+
+        controls_layout.addLayout(word_sub_layout)
+
         # Output voice format
         format_layout = QHBoxLayout()
         format_layout.setSpacing(7)
@@ -1707,7 +1867,7 @@ class abogen(QWidget):
         for pname in load_profiles().keys():
             self.voice_combo.addItem(profile_icon, pname, f"profile:{pname}")
         # re-add voices
-        for v in VOICES_INTERNAL:
+        for v in get_voices("kokoro"):
             icon = QIcon()
             flag_path = get_resource_path("abogen.assets.flags", f"{v[0]}.png")
             if flag_path and os.path.exists(flag_path):
@@ -1994,7 +2154,7 @@ class abogen(QWidget):
             )
 
             # CHECK GLOBAL OVERRIDE SETTING
-            if not self.config.get("queue_override_settings", False):
+            if not self.config.get("queue_override_settings", _DEFAULTS["queue_override_settings"]):
                 self.selected_lang = queued_item.lang_code
                 self.speed_slider.setValue(int(queued_item.speed * 100))
                 
@@ -2015,6 +2175,21 @@ class abogen(QWidget):
                 self.subtitle_speed_method = getattr(
                     queued_item, "subtitle_speed_method", "tts"
                 )
+                # Word substitution settings
+                self.word_substitutions_enabled = getattr(
+                    queued_item, "word_substitutions_enabled", False
+                )
+                self.word_substitutions_list = getattr(
+                    queued_item, "word_substitutions_list", ""
+                )
+                self.case_sensitive_substitutions = getattr(
+                    queued_item, "case_sensitive_substitutions", False
+                )
+                self.replace_all_caps = getattr(queued_item, "replace_all_caps", False)
+                self.replace_numerals = getattr(queued_item, "replace_numerals", False)
+                self.fix_nonstandard_punctuation = getattr(
+                    queued_item, "fix_nonstandard_punctuation", False
+                )
 
                 # This ensures that if conversion.py (or utils) reads from config/disk
                 # instead of using passed arguments, it sees the correct queue values.
@@ -2023,6 +2198,13 @@ class abogen(QWidget):
                 self.config["selected_format"] = self.selected_format
                 self.config["use_silent_gaps"] = self.use_silent_gaps
                 self.config["subtitle_speed_method"] = self.subtitle_speed_method
+                # Word substitution settings
+                self.config["word_substitutions_enabled"] = self.word_substitutions_enabled
+                self.config["word_substitutions_list"] = self.word_substitutions_list
+                self.config["case_sensitive_substitutions"] = self.case_sensitive_substitutions
+                self.config["replace_all_caps"] = self.replace_all_caps
+                self.config["replace_numerals"] = self.replace_numerals
+                self.config["fix_nonstandard_punctuation"] = self.fix_nonstandard_punctuation
 
                 # Sync Voice/Profile in config
                 self.config["selected_voice"] = self.selected_voice
@@ -2046,11 +2228,10 @@ class abogen(QWidget):
             self.current_queue_index = 0  # Reset for next time
 
     def get_voice_formula(self) -> str:
+        from abogen.voice_formulas import pairs_to_formula
+
         if self.mixed_voice_state:
-            formula_components = [
+            return pairs_to_formula(self.mixed_voice_state) or ""
-                f"{name}*{weight}" for name, weight in self.mixed_voice_state
-            ]
-            return " + ".join(filter(None, formula_components))
         else:
             return self.selected_voice
 
@@ -2128,9 +2309,9 @@ class abogen(QWidget):
             file_size_str = "Unknown"
 
         # pipeline_loaded_callback remains unchanged
-        def pipeline_loaded_callback(np_module, kpipeline_class, error):
+        def pipeline_loaded_callback(backend, error):
             if error:
-                self.update_log((f"Error loading numpy or KPipeline: {error}", "red"))
+                self.update_log((f"Error loading TTS backend: {error}", "red"))
                 prevent_sleep_end()
                 return
 
@@ -2153,8 +2334,7 @@ class abogen(QWidget):
                 self.selected_output_folder,
                 subtitle_mode=actual_subtitle_mode,
                 output_format=self.selected_format,
-                np_module=np_module,
+                backend=backend,
-                kpipeline_class=kpipeline_class,
                 start_time=self.start_time,
                 total_char_count=self.char_count,
                 use_gpu=self.gpu_ok,
@@ -2179,6 +2359,21 @@ class abogen(QWidget):
             self.conversion_thread.subtitle_speed_method = self.subtitle_speed_method
             # Pass use_spacy_segmentation setting
             self.conversion_thread.use_spacy_segmentation = self.use_spacy_segmentation
+            # Pass word substitution settings
+            self.conversion_thread.word_substitutions_enabled = (
+                self.word_substitutions_enabled
+            )
+            self.conversion_thread.word_substitutions_list = (
+                self.word_substitutions_list
+            )
+            self.conversion_thread.case_sensitive_substitutions = (
+                self.case_sensitive_substitutions
+            )
+            self.conversion_thread.replace_all_caps = self.replace_all_caps
+            self.conversion_thread.replace_numerals = self.replace_numerals
+            self.conversion_thread.fix_nonstandard_punctuation = (
+                self.fix_nonstandard_punctuation
+            )
             # Pass separate_chapters_format setting
             self.conversion_thread.separate_chapters_format = (
                 self.separate_chapters_format
@@ -2200,6 +2395,9 @@ class abogen(QWidget):
                 self.conversion_thread.merge_chapters_at_end = getattr(
                     self, "merge_chapters_at_end", True
                 )
+            # Pass intro/outro settings
+            self.conversion_thread.read_title_intro = self.read_title_intro
+            self.conversion_thread.read_closing_outro = self.read_closing_outro
             self.conversion_thread.progress_updated.connect(self.update_progress)
             self.conversion_thread.log_updated.connect(self.update_log)
             self.conversion_thread.conversion_finished.connect(
@@ -2223,7 +2421,11 @@ class abogen(QWidget):
             self.gpu_ok = gpu_ok
             self.update_log((gpu_msg, gpu_ok))
             self.update_log("Loading modules...")
-            load_thread = LoadPipelineThread(pipeline_loaded_callback)
+
+            lang_code = self.selected_lang or "a"
+            load_thread = LoadPipelineThread(
+                pipeline_loaded_callback, lang_code=lang_code, use_gpu=gpu_ok
+            )
             load_thread.start()
 
         threading.Thread(target=gpu_and_load, daemon=True).start()
@@ -2234,7 +2436,7 @@ class abogen(QWidget):
             return
 
         # Check if override was active (this determines which settings were ACTUALLY used)
-        override_active = self.config.get("queue_override_settings", False)
+        override_active = self.config.get("queue_override_settings", _DEFAULTS["queue_override_settings"])
 
         # If override is ON, capture the global settings that were used for processing
         if override_active:
@@ -2660,18 +2862,18 @@ class abogen(QWidget):
             )
             self.loading_movie.start()
 
-        def pipeline_loaded_callback(np_module, kpipeline_class, error):
+        lang = self.selected_lang or "a"
-            self._on_pipeline_loaded_for_preview(np_module, kpipeline_class, error)
+        load_thread = LoadPipelineThread(
-
+            self._on_pipeline_loaded_for_preview, lang_code=lang, use_gpu=self.gpu_ok
-        load_thread = LoadPipelineThread(pipeline_loaded_callback)
+        )
         load_thread.start()
 
-    def _on_pipeline_loaded_for_preview(self, np_module, kpipeline_class, error):
+    def _on_pipeline_loaded_for_preview(self, backend, error):
         # stop loading animation and restore icon on error
         if error:
             self.loading_movie.stop()
             self._show_error_message_box(
-                "Loading Error", f"Error loading numpy or KPipeline: {error}"
+                "Loading Error", f"Error loading TTS backend: {error}"
             )
             self.btn_preview.setIcon(self.play_icon)
             self.btn_preview.setEnabled(True)
@@ -2709,7 +2911,7 @@ class abogen(QWidget):
         gpu_msg, gpu_ok = get_gpu_acceleration(self.use_gpu)
 
         self.preview_thread = VoicePreviewThread(
-            np_module, kpipeline_class, lang, voice, speed, gpu_ok
+            backend, lang, voice, speed, gpu_ok
         )
         self.preview_thread.finished.connect(self._play_preview_audio)
         self.preview_thread.error.connect(self._preview_error)
@@ -2927,6 +3129,41 @@ class abogen(QWidget):
         self.config["use_gpu"] = self.use_gpu
         save_config(self.config)
 
+    def on_word_sub_changed(self, text):
+        """Handle word substitution dropdown change."""
+        self.word_substitutions_enabled = text == "Enabled"
+        self.btn_word_sub_settings.setEnabled(self.word_substitutions_enabled)
+
+        # Save to config
+        self.config["word_substitutions_enabled"] = self.word_substitutions_enabled
+        save_config(self.config)
+
+    def show_word_sub_dialog(self):
+        """Show word substitutions settings dialog."""
+        dialog = WordSubstitutionsDialog(
+            self,
+            initial_list=self.word_substitutions_list,
+            initial_case_sensitive=self.case_sensitive_substitutions,
+            initial_caps=self.replace_all_caps,
+            initial_numerals=self.replace_numerals,
+            initial_punctuation=self.fix_nonstandard_punctuation,
+        )
+
+        if dialog.exec() == QDialog.DialogCode.Accepted:
+            self.word_substitutions_list = dialog.get_substitutions_list()
+            self.case_sensitive_substitutions = dialog.get_case_sensitive()
+            self.replace_all_caps = dialog.get_replace_all_caps()
+            self.replace_numerals = dialog.get_replace_numerals()
+            self.fix_nonstandard_punctuation = dialog.get_fix_nonstandard_punctuation()
+
+            # Save all settings to config
+            self.config["word_substitutions_list"] = self.word_substitutions_list
+            self.config["case_sensitive_substitutions"] = self.case_sensitive_substitutions
+            self.config["replace_all_caps"] = self.replace_all_caps
+            self.config["replace_numerals"] = self.replace_numerals
+            self.config["fix_nonstandard_punctuation"] = self.fix_nonstandard_punctuation
+            save_config(self.config)
+
     def cleanup_conversion_thread(self):
         # Stop conversion thread
         if (
@@ -2977,12 +3214,16 @@ class abogen(QWidget):
             )
             box.setDefaultButton(QMessageBox.StandardButton.No)
             if box.exec() == QMessageBox.StandardButton.Yes:
+                from abogen import shutdown
+                shutdown.request_shutdown()
                 self.cleanup_conversion_thread()
                 self.cleanup_preview_threads()
                 event.accept()
             else:
                 event.ignore()
         else:
+            from abogen import shutdown
+            shutdown.request_shutdown()
             self.cleanup_conversion_thread()
             self.cleanup_preview_threads()
             event.accept()
@@ -2991,8 +3232,6 @@ class abogen(QWidget):
         """Show dialog to ask user about chapter processing options when chapters are detected in a .txt file"""
         # Check if this is a timestamp detection (-1) or chapter detection
         if chapter_count == -1:
-            from abogen.conversion import TimestampDetectionDialog
-
             dialog = TimestampDetectionDialog(parent=self)
             dialog.setWindowModality(Qt.WindowModality.ApplicationModal)
 
@@ -3007,8 +3246,6 @@ class abogen(QWidget):
             return
 
         # Normal chapter detection
-        from abogen.conversion import ChapterOptionsDialog
-
         dialog = ChapterOptionsDialog(chapter_count, parent=self)
         dialog.setWindowModality(Qt.WindowModality.ApplicationModal)
 
@@ -3175,7 +3412,7 @@ class abogen(QWidget):
         app.installEventFilter(app._dark_titlebar_event_filter)
 
         # Save config if changed
-        if self.config.get("theme", "system") != theme:
+        if self.config.get("theme", _DEFAULTS["theme"]) != theme:
             self.config["theme"] = theme
             save_config(self.config)
 
@@ -3197,7 +3434,7 @@ class abogen(QWidget):
         ]
 
         # Get current theme from config, default to "system"
-        current_theme = self.config.get("theme", "system")
+        current_theme = self.config.get("theme", _DEFAULTS["theme"])
         for value, text in theme_options:
             theme_action = QAction(text, self)
             theme_action.setCheckable(True)
@@ -3328,6 +3565,27 @@ class abogen(QWidget):
         # Add separator
         menu.addSeparator()
 
+        # Add title intro option
+        self.title_intro_action = QAction("Read title intro before first chapter", self)
+        self.title_intro_action.setCheckable(True)
+        self.title_intro_action.setChecked(self.read_title_intro)
+        self.title_intro_action.triggered.connect(
+            lambda checked: self.toggle_read_title_intro(checked)
+        )
+        menu.addAction(self.title_intro_action)
+
+        # Add closing outro option
+        self.closing_outro_action = QAction("Read closing outro after last chapter", self)
+        self.closing_outro_action.setCheckable(True)
+        self.closing_outro_action.setChecked(self.read_closing_outro)
+        self.closing_outro_action.triggered.connect(
+            lambda checked: self.toggle_read_closing_outro(checked)
+        )
+        menu.addAction(self.closing_outro_action)
+
+        # Add separator
+        menu.addSeparator()
+
         # Add "Pre-download models and voices for offline use" option
         predownload_action = QAction(
             "Pre-download models and voices for offline use", self
@@ -3339,7 +3597,7 @@ class abogen(QWidget):
         disable_kokoro_action = QAction("Disable Kokoro's internet access", self)
         disable_kokoro_action.setCheckable(True)
         disable_kokoro_action.setChecked(
-            self.config.get("disable_kokoro_internet", False)
+            self.config.get("disable_kokoro_internet", _DEFAULTS["disable_kokoro_internet"])
         )
         disable_kokoro_action.triggered.connect(
             lambda checked: self.toggle_kokoro_internet_access(checked)
@@ -3349,7 +3607,7 @@ class abogen(QWidget):
         # Add check for updates option
         check_updates_action = QAction("Check for updates at startup", self)
         check_updates_action.setCheckable(True)
-        check_updates_action.setChecked(self.config.get("check_updates", True))
+        check_updates_action.setChecked(self.config.get("check_updates", _DEFAULTS["check_updates"]))
         check_updates_action.triggered.connect(self.toggle_check_updates)
         menu.addAction(check_updates_action)
 
@@ -3404,6 +3662,16 @@ class abogen(QWidget):
         self.config["use_spacy_segmentation"] = enabled
         save_config(self.config)
 
+    def toggle_read_title_intro(self, enabled):
+        self.read_title_intro = enabled
+        self.config["read_title_intro"] = enabled
+        save_config(self.config)
+
+    def toggle_read_closing_outro(self, enabled):
+        self.read_closing_outro = enabled
+        self.config["read_closing_outro"] = enabled
+        save_config(self.config)
+
     def restart_app(self):
 
         import sys
@@ -3975,7 +4243,7 @@ Categories=AudioVideo;Audio;Utility;
         """Open a dialog to set the maximum words per subtitle"""
         from PyQt6.QtWidgets import QInputDialog
 
-        current_value = self.config.get("max_subtitle_words", 50)
+        current_value = self.config.get("max_subtitle_words", _DEFAULTS["max_subtitle_words"])
 
         value, ok = QInputDialog.getInt(
             self,
@@ -4003,7 +4271,7 @@ Categories=AudioVideo;Audio;Utility;
     def set_silence_between_chapters(self):
         """Open a dialog to set the silence duration between chapters"""
 
-        current_value = self.config.get("silence_duration", 2.0)
+        current_value = self.config.get("silence_duration", _DEFAULTS.get("silence_between_chapters", 2.0))
 
         dlg = QInputDialog(self)
         dlg.setWindowTitle("Silence Duration (seconds)")

abogen/pyqt/main.py

@@ -1,10 +1,10 @@
 import os
 import sys
 import platform
-import atexit
-import signal
-from abogen.utils import get_resource_path, load_config, prevent_sleep_end
 
+# Initialise global shutdown handling (atexit, signals, Qt) as early as possible.
+from abogen import shutdown  # noqa: F401
+shutdown.register_shutdown()
 
 # Fix PyTorch DLL loading issue ([WinError 1114]) on Windows before importing PyQt6
 if platform.system() == "Windows":
@@ -94,6 +94,7 @@ os.environ["HF_HUB_DISABLE_TELEMETRY"] = "1"  # Disable Hugging Face telemetry
 os.environ["HF_HUB_ETAG_TIMEOUT"] = "10"  # Metadata request timeout (seconds)
 os.environ["HF_HUB_DOWNLOAD_TIMEOUT"] = "10"  # File download timeout (seconds)
 os.environ["HF_HUB_DISABLE_SYMLINKS_WARNING"] = "1"  # Disable symlinks warning
+from abogen.utils import load_config
 if load_config().get("disable_kokoro_internet", False):
     print("INFO: Kokoro's internet access is disabled.")
     os.environ["HF_HUB_OFFLINE"] = "1"  # Disable Hugging Face Hub internet access
@@ -105,25 +106,6 @@ from abogen.constants import PROGRAM_NAME, VERSION
 os.environ["MIOPEN_FIND_MODE"] = "FAST"
 os.environ["MIOPEN_CONV_PRECISE_ROCM_TUNING"] = "0"
 
-# Reset sleep states
-atexit.register(prevent_sleep_end)
-
-
-# Also handle signals (Ctrl+C, kill, etc.)
-def _cleanup_sleep(signum, frame):
-    prevent_sleep_end()
-    sys.exit(0)
-
-
-signal.signal(signal.SIGINT, _cleanup_sleep)
-signal.signal(signal.SIGTERM, _cleanup_sleep)
-
-# Ensure sys.stdout and sys.stderr are valid in GUI mode
-if sys.stdout is None:
-    sys.stdout = open(os.devnull, "w")
-if sys.stderr is None:
-    sys.stderr = open(os.devnull, "w")
-
 # Enable MPS GPU acceleration on Mac Apple Silicon
 if platform.system() == "Darwin" and platform.processor() == "arm":
     os.environ["PYTORCH_ENABLE_MPS_FALLBACK"] = "1"

abogen/pyqt/predownload_gui.py

@@ -21,7 +21,8 @@ from PyQt6.QtWidgets import (
 )
 from PyQt6.QtCore import QThread, pyqtSignal
 
-from abogen.constants import COLORS, VOICES_INTERNAL
+from abogen.constants import COLORS
+from abogen.tts_plugin.utils import get_voices
 from abogen.spacy_utils import SPACY_MODELS
 import abogen.hf_tracker
 
@@ -114,7 +115,7 @@ class PreDownloadWorker(QThread):
             self._voices_success = False
             return
 
-        voice_list = VOICES_INTERNAL
+        voice_list = get_voices("kokoro")
         for idx, voice in enumerate(voice_list, start=1):
             if self._cancelled:
                 self._voices_success = False
@@ -462,14 +463,14 @@ class PreDownloadDialog(QDialog):
         try:
             from huggingface_hub import try_to_load_from_cache
 
-            for voice in VOICES_INTERNAL:
+            for voice in get_voices("kokoro"):
                 if not try_to_load_from_cache(
                     repo_id="hexgrad/Kokoro-82M", filename=f"voices/{voice}.pt"
                 ):
                     missing.append(voice)
         except Exception:
             # If HF missing, report all as missing
-            return False, list(VOICES_INTERNAL)
+            return False, list(get_voices("kokoro"))
         return (len(missing) == 0), missing
 
     def _check_kokoro_model(self) -> bool:

abogen/pyqt/queue_manager_gui.py

@@ -35,6 +35,12 @@ OVERRIDE_FIELDS = [
     "replace_single_newlines",
     "use_silent_gaps",
     "subtitle_speed_method",
+    "word_substitutions_enabled",
+    "word_substitutions_list",
+    "case_sensitive_substitutions",
+    "replace_all_caps",
+    "replace_numerals",
+    "fix_nonstandard_punctuation",
 ]
 
 
@@ -474,6 +480,21 @@ class QueueManager(QDialog):
             attrs["subtitle_speed_method"] = getattr(
                 parent, "subtitle_speed_method", "tts"
             )
+            # word substitutions
+            attrs["word_substitutions_enabled"] = getattr(
+                parent, "word_substitutions_enabled", False
+            )
+            attrs["word_substitutions_list"] = getattr(
+                parent, "word_substitutions_list", ""
+            )
+            attrs["case_sensitive_substitutions"] = getattr(
+                parent, "case_sensitive_substitutions", False
+            )
+            attrs["replace_all_caps"] = getattr(parent, "replace_all_caps", False)
+            attrs["replace_numerals"] = getattr(parent, "replace_numerals", False)
+            attrs["fix_nonstandard_punctuation"] = getattr(
+                parent, "fix_nonstandard_punctuation", False
+            )
             # book handler options
             attrs["save_chapters_separately"] = getattr(
                 parent, "save_chapters_separately", None

abogen/pyqt/queued_item.py

@@ -19,3 +19,10 @@ class QueuedItem:
     save_base_path: str = None
     save_chapters_separately: bool = None
     merge_chapters_at_end: bool = None
+    # Word Substitution fields
+    word_substitutions_enabled: bool = False
+    word_substitutions_list: str = ""
+    case_sensitive_substitutions: bool = False
+    replace_all_caps: bool = False
+    replace_numerals: bool = False
+    fix_nonstandard_punctuation: bool = False

abogen/pyqt/voice_formula_gui.py

@@ -28,11 +28,11 @@ from PyQt6.QtWidgets import (
 from PyQt6.QtCore import Qt, QTimer, QPoint, QRect, QSize
 from PyQt6.QtGui import QPixmap, QIcon, QAction
 from abogen.constants import (
-    VOICES_INTERNAL,
     SUPPORTED_LANGUAGES_FOR_SUBTITLE_GENERATION,
     LANGUAGE_DESCRIPTIONS,
     COLORS,
 )
+from abogen.tts_plugin.utils import get_voices
 import re
 import platform
 from abogen.utils import get_resource_path
@@ -179,7 +179,7 @@ class VoiceMixer(QWidget):
         layout.addWidget(QLabel(name), alignment=Qt.AlignmentFlag.AlignCenter)
 
         # Voice name label with gender icon
-        is_female = self.voice_name in VOICES_INTERNAL and self.voice_name[1] == "f"
+        is_female = self.voice_name in get_voices("kokoro") and self.voice_name[1] == "f"
 
         # Icons layout (flag and gender)
         icons_layout = QHBoxLayout()
@@ -772,7 +772,7 @@ class VoiceFormulaDialog(QDialog):
 
     def add_voices(self, initial_state):
         first_enabled_voice = None
-        for voice in VOICES_INTERNAL:
+        for voice in get_voices("kokoro"):
             language_code = voice[0]  # First character is the language code
             matching_voice = next(
                 (item for item in initial_state if item[0] == voice), None

abogen/shutdown.py

@@ -0,0 +1,160 @@
+"""Graceful shutdown - single module, no over-engineering."""
+from __future__ import annotations
+
+import atexit
+import gc
+import signal
+import sys
+from typing import Callable
+
+_CLEANUP_FUNCS: list[Callable[[], None]] = []
+_EXECUTED = False
+
+
+def register_cleanup(fn: Callable[[], None]) -> None:
+    """Register a cleanup function to run on shutdown."""
+    _CLEANUP_FUNCS.append(fn)
+
+
+def _run_cleanups() -> None:
+    global _EXECUTED
+    if _EXECUTED:
+        return
+    _EXECUTED = True
+    for fn in _CLEANUP_FUNCS:
+        try:
+            fn()
+        except Exception:
+            pass
+
+
+# ---- Register built-in cleanup functions ----
+
+# 1. Restore sleep prevention
+def _restore_sleep() -> None:
+    try:
+        from abogen.utils import prevent_sleep_end
+        prevent_sleep_end()
+    except Exception:
+        pass
+
+register_cleanup(_restore_sleep)
+
+# 2. Shutdown web UI ConversionService
+def _shutdown_conversion_service() -> None:
+    try:
+        from abogen.webui.service import get_service
+        svc = get_service()
+        if svc is not None:
+            svc.shutdown()
+    except Exception:
+        pass
+
+register_cleanup(_shutdown_conversion_service)
+
+# 3. Clear TTS pipelines and GPU memory
+def _cleanup_tts_pipelines() -> None:
+    # Clear web UI pipeline cache
+    try:
+        from abogen.webui.conversion_runner import _PIPELINES
+        _PIPELINES.clear()
+    except Exception:
+        pass
+
+    # Clear PyQt conversion thread voice cache
+    try:
+        from abogen.pyqt.conversion import ConversionThread
+        if hasattr(ConversionThread, "voice_cache"):
+            ConversionThread.voice_cache.clear()
+    except Exception:
+        pass
+
+    gc.collect()
+
+    # Release CUDA cache
+    try:
+        import torch
+        if torch.cuda.is_available():
+            torch.cuda.empty_cache()
+            torch.cuda.ipc_collect()
+    except Exception:
+        pass
+
+register_cleanup(_cleanup_tts_pipelines)
+
+# 4. Clear global voice cache
+def _clear_voice_cache() -> None:
+    try:
+        from abogen.voice_cache import clear_voice_cache
+        clear_voice_cache()
+    except Exception:
+        pass
+
+register_cleanup(_clear_voice_cache)
+
+# 5. Terminate child processes (ffmpeg, etc.)
+def _terminate_subprocesses() -> None:
+    try:
+        import psutil
+    except Exception:
+        return
+
+    try:
+        current = psutil.Process()
+        for child in current.children(recursive=True):
+            try:
+                child.terminate()
+            except Exception:
+                pass
+        gone, alive = psutil.wait_procs(current.children(recursive=True), timeout=3)
+        for proc in alive:
+            try:
+                proc.kill()
+            except Exception:
+                pass
+    except Exception:
+        pass
+
+register_cleanup(_terminate_subprocesses)
+
+
+def register_shutdown() -> None:
+    """Install process-wide shutdown hooks (atexit, signals, Qt)."""
+    if register_shutdown._registered:
+        return
+    register_shutdown._registered = True
+
+    atexit.register(_run_cleanups)
+
+    # POSIX signals
+    for sig in (signal.SIGINT, signal.SIGTERM):
+        try:
+            signal.signal(sig, _on_signal)
+        except Exception:
+            pass
+
+    # Qt hook
+    try:
+        from PyQt6.QtWidgets import QApplication
+
+        app = QApplication.instance()
+        if app is not None:
+            app.aboutToQuit.connect(_run_cleanups)
+    except Exception:
+        pass
+
+
+register_shutdown._registered = False
+
+
+def _on_signal(signum: int, _frame) -> None:
+    _run_cleanups()
+    sys.exit(0)
+
+
+def request_shutdown() -> None:
+    """Programmatically trigger cleanup (e.g., from GUI closeEvent)."""
+    _run_cleanups()
+
+
+__all__ = ["register_shutdown", "request_shutdown", "register_cleanup"]

abogen/subtitle_utils.py

@@ -15,6 +15,8 @@ _ASS_STYLING_PATTERN = re.compile(r"\{[^}]+\}")
 _ASS_NEWLINE_N_PATTERN = re.compile(r"\\N")
 _ASS_NEWLINE_LOWER_N_PATTERN = re.compile(r"\\n")
 _CHAPTER_MARKER_SEARCH_PATTERN = re.compile(r"<<CHAPTER_MARKER:(.*?)>>")
+_VOICE_MARKER_PATTERN = re.compile(r"<<VOICE:[^>]*>>")
+_VOICE_MARKER_SEARCH_PATTERN = re.compile(r"<<VOICE:(.*?)>>")
 _WEBVTT_HEADER_PATTERN = re.compile(r"^WEBVTT.*?\n", re.MULTILINE)
 _VTT_STYLE_PATTERN = re.compile(r"STYLE\s*\n.*?(?=\n\n|$)", re.DOTALL)
 _VTT_NOTE_PATTERN = re.compile(r"NOTE\s*\n.*?(?=\n\n|$)", re.DOTALL)
@@ -31,17 +33,19 @@ _LINUX_ILLEGAL_CHARS_PATTERN = re.compile(r"[/\x00]")
 
 
 def clean_subtitle_text(text):
-    """Remove chapter markers and metadata tags from subtitle text."""
+    """Remove chapter markers, voice markers, and metadata tags from subtitle text."""
     # Use pre-compiled patterns for better performance
     text = _METADATA_TAG_PATTERN.sub("", text)
     text = _CHAPTER_MARKER_PATTERN.sub("", text)
+    text = _VOICE_MARKER_PATTERN.sub("", text)
     return text.strip()
 
 
 def calculate_text_length(text):
     # Use pre-compiled patterns for better performance
-    # Ignore chapter markers and metadata patterns in a single pass
+    # Ignore chapter markers, voice markers, and metadata patterns in a single pass
     text = _CHAPTER_MARKER_PATTERN.sub("", text)
+    text = _VOICE_MARKER_PATTERN.sub("", text)
     text = _METADATA_TAG_PATTERN.sub("", text)
     # Ignore newlines and leading/trailing spaces
     text = text.replace("\n", "").strip()
@@ -459,3 +463,122 @@ def sanitize_name_for_os(name, is_folder=True):
         sanitized = sanitized[:255].rstrip(". ")
 
     return sanitized
+
+
+def validate_voice_name(voice_name):
+    """Validate voice name against available voices (case-insensitive).
+    Handles both single voices and formulas like 'af_heart*0.5 + am_echo*0.5'.
+
+    Args:
+        voice_name: Voice name or formula string to validate
+
+    Returns:
+        Tuple of (is_valid, invalid_voice_name):
+            - is_valid: True if all voices in the name/formula are valid
+            - invalid_voice_name: The first invalid voice found, or None if all valid
+    """
+    from abogen.tts_plugin.utils import get_voices
+
+    # Create case-insensitive lookup set (done once per call)
+    voice_lookup_lower = {v.lower() for v in get_voices("kokoro")}
+    voice_name = voice_name.strip()
+
+    # Check if it's a formula (contains *)
+    if "*" in voice_name:
+        # Extract voice names from formula
+        voices = voice_name.split("+")
+        for term in voices:
+            if "*" in term:
+                base_voice = term.split("*")[0].strip()
+                # Case-insensitive comparison
+                if base_voice.lower() not in voice_lookup_lower:
+                    return False, base_voice
+        return True, None
+    else:
+        # Single voice - case-insensitive comparison
+        if voice_name.lower() not in voice_lookup_lower:
+            return False, voice_name
+        return True, None
+
+
+def split_text_by_voice_markers(text, default_voice):
+    """Split text by voice markers, returning list of (voice, text) tuples.
+
+    IMPORTANT: Returns the last voice used so it can persist across chapters.
+    Voice names are normalized to lowercase to match canonical voice names.
+
+    Args:
+        text: Text potentially containing <<VOICE:name>> markers
+        default_voice: Voice to use if no markers found or before first marker
+
+    Returns:
+        Tuple of (segments_list, last_voice_used, valid_count, invalid_count):
+            - segments_list: List of (voice_name, segment_text) tuples
+            - last_voice_used: The voice that should continue into next chapter
+            - valid_count: Number of valid voice markers processed
+            - invalid_count: Number of invalid voice markers skipped
+    """
+    from abogen.tts_plugin.utils import get_voices
+
+    voice_splits = list(_VOICE_MARKER_SEARCH_PATTERN.finditer(text))
+
+    if not voice_splits:
+        # No voice markers, return entire text with default voice
+        return [(default_voice, text)], default_voice, 0, 0
+
+    segments = []
+    current_voice = default_voice
+    valid_markers = 0
+    invalid_markers = 0
+
+    # Text before first marker uses default voice
+    first_start = voice_splits[0].start()
+    if first_start > 0:
+        intro_text = text[:first_start].strip()
+        if intro_text:
+            segments.append((current_voice, intro_text))
+
+    # Process each voice marker
+    for idx, match in enumerate(voice_splits):
+        voice_name = match.group(1).strip()
+        start = match.end()
+        end = voice_splits[idx + 1].start() if idx + 1 < len(voice_splits) else len(text)
+        segment_text = text[start:end].strip()
+
+        # Validate voice name
+        is_valid, invalid_voice = validate_voice_name(voice_name)
+        if is_valid:
+            # Normalize to lowercase to match canonical form
+            # Handle both single voices and formulas
+            if "*" in voice_name:
+                # Normalize each voice in the formula
+                normalized_parts = []
+                for part in voice_name.split("+"):
+                    part = part.strip()
+                    if "*" in part:
+                        voice_part, weight = part.split("*", 1)
+                        # Find the canonical (lowercase) voice name
+                        voice_part_lower = voice_part.strip().lower()
+                        canonical_voice = next(
+                            (v for v in get_voices("kokoro") if v.lower() == voice_part_lower),
+                            voice_part.strip()
+                        )
+                        normalized_parts.append(f"{canonical_voice}*{weight.strip()}")
+                current_voice = " + ".join(normalized_parts)
+            else:
+                # Find the canonical (lowercase) voice name
+                voice_name_lower = voice_name.lower()
+                current_voice = next(
+                    (v for v in get_voices("kokoro") if v.lower() == voice_name_lower),
+                    voice_name
+                )
+            valid_markers += 1
+        else:
+            # Invalid voice - stay with previous voice
+            invalid_markers += 1
+
+        if segment_text:
+            segments.append((current_voice, segment_text))
+
+    # Return segments, last voice, and counts
+    return segments, current_voice, valid_markers, invalid_markers

abogen/text_extractor.py

@@ -1023,8 +1023,13 @@ class EpubExtractor:
         if not html:
             return ""
         soup = BeautifulSoup(html, "html.parser")
-        for tag in soup.find_all(["p", "div"]):
+
+        # Add line breaks after block-level elements to ensure pauses in speech
+        for tag in soup.find_all(
+            ["p", "div", "h1", "h2", "h3", "h4", "h5", "h6", "li", "blockquote"]
+        ):
             tag.append("\n\n")
+
         for ol in soup.find_all("ol"):
             start_attr = ol.get("start")
             try:

abogen/tts_plugin/__init__.py

@@ -0,0 +1,170 @@
+"""TTS Plugin Architecture - Public API.
+
+This package defines the frozen Plugin API for the TTS Plugin Architecture.
+All public interfaces are fully defined but contain no business logic.
+
+Public modules:
+- types: Core domain value objects (AudioFormat, Duration, VoiceSelection, etc.)
+- errors: Error hierarchy (EngineError and subtypes)
+- manifest: Plugin manifest types (PluginManifest, EngineManifest, etc.)
+- engine: Engine and EngineSession protocols
+- capabilities: Optional capability interfaces (VoiceLister, PreviewGenerator, etc.)
+- host_context: HostContext dataclass
+- plugin: Plugin contract (create_engine function signature)
+- loader: Plugin discovery and loading
+- plugin_manager: Plugin management and engine creation
+- utils: Direct utility functions (get_voices, create_pipeline, etc.)
+
+Usage:
+    from abogen.tts_plugin import (
+        # Types
+        AudioFormat,
+        Duration,
+        VoiceSelection,
+        ParameterValues,
+        SynthesisRequest,
+        SynthesizedAudio,
+        EngineConfig,
+        # Errors
+        EngineError,
+        ModelNotFoundError,
+        ModelLoadError,
+        NetworkError,
+        InvalidInputError,
+        ConfigurationError,
+        CancelledError,
+        InternalError,
+        # Manifest
+        PluginManifest,
+        EngineManifest,
+        VoiceSourceManifest,
+        VoiceManifest,
+        ParameterManifest,
+        AudioFormatManifest,
+        EnumOption,
+        RequirementManifest,
+        GpuRequirement,
+        ModelManifest,
+        # Engine
+        Engine,
+        EngineSession,
+        # Capabilities
+        VoiceLister,
+        PreviewGenerator,
+        StreamingSynthesizer,
+        CancelableSession,
+        # Host Context
+        HostContext,
+        HttpClient,
+        # Plugin Manager
+        get_plugin_manager,
+        reset_plugin_manager,
+        # Utils
+        get_voices,
+        get_default_voice,
+        is_plugin_registered,
+        resolve_voice_to_plugin,
+        create_pipeline,
+    )
+"""
+
+from abogen.tts_plugin.capabilities import (
+    CancelableSession,
+    PreviewGenerator,
+    StreamingSynthesizer,
+    VoiceLister,
+)
+from abogen.tts_plugin.engine import Engine, EngineSession
+from abogen.tts_plugin.errors import (
+    CancelledError,
+    ConfigurationError,
+    EngineError,
+    InternalError,
+    InvalidInputError,
+    ModelLoadError,
+    ModelNotFoundError,
+    NetworkError,
+)
+from abogen.tts_plugin.host_context import HttpClient, HostContext
+from abogen.tts_plugin.manifest import (
+    AudioFormatManifest,
+    EngineManifest,
+    EnumOption,
+    GpuRequirement,
+    ModelManifest,
+    ParameterManifest,
+    PluginManifest,
+    RequirementManifest,
+    VoiceManifest,
+    VoiceSourceManifest,
+)
+from abogen.tts_plugin.types import (
+    AudioFormat,
+    Duration,
+    EngineConfig,
+    ParameterValues,
+    SynthesisRequest,
+    SynthesizedAudio,
+    VoiceSelection,
+)
+
+# Plugin Manager and Utils
+from abogen.tts_plugin.plugin_manager import get_plugin_manager, reset_plugin_manager
+from abogen.tts_plugin.utils import (
+    create_pipeline,
+    get_default_voice,
+    get_voices,
+    is_plugin_registered,
+    resolve_voice_to_plugin,
+)
+
+__all__ = [
+    # Types
+    "AudioFormat",
+    "Duration",
+    "VoiceSelection",
+    "ParameterValues",
+    "SynthesisRequest",
+    "SynthesizedAudio",
+    "EngineConfig",
+    # Errors
+    "EngineError",
+    "ModelNotFoundError",
+    "ModelLoadError",
+    "NetworkError",
+    "InvalidInputError",
+    "ConfigurationError",
+    "CancelledError",
+    "InternalError",
+    # Manifest
+    "PluginManifest",
+    "EngineManifest",
+    "VoiceSourceManifest",
+    "VoiceManifest",
+    "ParameterManifest",
+    "AudioFormatManifest",
+    "EnumOption",
+    "RequirementManifest",
+    "GpuRequirement",
+    "ModelManifest",
+    # Engine
+    "Engine",
+    "EngineSession",
+    # Capabilities
+    "VoiceLister",
+    "PreviewGenerator",
+    "StreamingSynthesizer",
+    "CancelableSession",
+    # Host Context
+    "HostContext",
+    "HttpClient",
+    # Plugin Manager
+    "get_plugin_manager",
+    "reset_plugin_manager",
+    # Utils
+    "get_voices",
+    "get_default_voice",
+    "is_plugin_registered",
+    "resolve_voice_to_plugin",
+    "create_pipeline",
+]

abogen/tts_plugin/capabilities.py

@@ -0,0 +1,103 @@
+"""Capability interfaces for the TTS Plugin Architecture.
+
+This module defines optional capability interfaces that engines can implement.
+Capabilities are additive; implementing new capabilities doesn't break old plugins.
+"""
+
+from __future__ import annotations
+
+from typing import Iterator, Protocol, runtime_checkable
+
+from abogen.tts_plugin.manifest import VoiceManifest
+from abogen.tts_plugin.types import SynthesisRequest, SynthesizedAudio, VoiceSelection
+
+
+@runtime_checkable
+class VoiceLister(Protocol):
+    """Protocol for listing available voices.
+
+    Engines that support voice listing should implement this interface.
+    """
+
+    def listVoices(self, sourceId: str) -> list[VoiceManifest]:
+        """List available voices for a given source.
+
+        Args:
+            sourceId: The voice source identifier.
+
+        Returns:
+            List of VoiceManifest describing available voices.
+
+        Raises:
+            EngineError: On failure.
+        """
+        ...
+
+
+@runtime_checkable
+class PreviewGenerator(Protocol):
+    """Protocol for generating voice previews.
+
+    Engines that support voice preview should implement this interface.
+    """
+
+    def generatePreview(self, voice: VoiceSelection, text: str) -> SynthesizedAudio:
+        """Generate a preview audio for a voice.
+
+        Args:
+            voice: Voice selection for the preview.
+            text: Text to use for the preview.
+
+        Returns:
+            SynthesizedAudio with the preview audio data.
+
+        Raises:
+            EngineError: On failure.
+        """
+        ...
+
+
+@runtime_checkable
+class StreamingSynthesizer(Protocol):
+    """Protocol for streaming synthesis.
+
+    Optional capability of EngineSession, not Engine.
+    Engines that support streaming synthesis should implement this interface.
+    """
+
+    def synthesizeStream(self, request: SynthesisRequest) -> Iterator[bytes]:
+        """Synthesize audio in streaming mode.
+
+        Args:
+            request: The synthesis request.
+
+        Yields:
+            Audio chunks as they become available.
+
+        Raises:
+            CancelledError: If cancel() is called during iteration.
+            EngineError: On synthesis failure.
+        """
+        ...
+        # This is a generator function; implementation will use yield
+        yield b""  # pragma: no cover
+
+
+@runtime_checkable
+class CancelableSession(Protocol):
+    """Protocol for cancellation support.
+
+    Optional capability for engines that support cancellation.
+    cancel() causes synthesize() to raise CancelledError.
+    """
+
+    def cancel(self) -> None:
+        """Cancel in-progress synthesis.
+
+        After cancellation, synthesize() raises CancelledError.
+        The session remains usable after cancellation.
+
+        Raises:
+            EngineError: If called after dispose().
+        """
+        ...

abogen/tts_plugin/engine.py

@@ -0,0 +1,95 @@
+"""Engine interfaces for the TTS Plugin Architecture.
+
+This module defines the core Engine and EngineSession protocols.
+These are the primary interfaces that plugin implementations must satisfy.
+"""
+
+from __future__ import annotations
+
+from typing import Protocol, runtime_checkable
+
+from abogen.tts_plugin.types import SynthesisRequest, SynthesizedAudio
+
+
+@runtime_checkable
+class EngineSession(Protocol):
+    """Protocol for a session that owns mutable execution state.
+
+    An EngineSession is created by Engine.createSession() and owns
+    mutable execution state isolated from other concurrent work.
+    It is NOT thread-safe.
+
+    Lifecycle:
+        1. Created by Engine.createSession()
+        2. Used for synthesis via synthesize()
+        3. Disposed via dispose()
+
+    After dispose(), all methods except dispose() raise EngineError.
+    """
+
+    def synthesize(self, request: SynthesisRequest) -> SynthesizedAudio:
+        """Synthesize audio from text.
+
+        Args:
+            request: The synthesis request containing text, voice, parameters, and format.
+
+        Returns:
+            SynthesizedAudio with the synthesized audio data.
+
+        Raises:
+            EngineError: On synthesis failure. Session remains usable after error.
+            EngineError: If called after dispose().
+        """
+        ...
+
+    def dispose(self) -> None:
+        """Release session resources.
+
+        This method is idempotent and safe to call multiple times.
+        It never raises exceptions (catches and logs internally).
+        After dispose(), all methods except dispose() raise EngineError.
+        """
+        ...
+
+
+@runtime_checkable
+class Engine(Protocol):
+    """Protocol for a TTS engine that creates sessions.
+
+    An Engine is a factory for EngineSession instances. It is stateless
+    and thread-safe for createSession().
+
+    Lifecycle:
+        1. Created via create_engine() (plugin contract)
+        2. Sessions created via createSession()
+        3. Disposed via dispose()
+
+    Thread Safety:
+        - createSession() is thread-safe and can be called from any thread.
+        - dispose() must be called after all sessions are disposed.
+        - Disposing engine while sessions are alive violates API contract.
+    """
+
+    def createSession(self) -> EngineSession:
+        """Create a new session for synthesis.
+
+        Returns:
+            A new EngineSession instance. Ownership transfers to caller.
+
+        Raises:
+            EngineError: On failure. No partially initialized session is returned.
+        """
+        ...
+
+    def dispose(self) -> None:
+        """Release engine resources.
+
+        Caller must ensure all sessions created by this engine are disposed
+        before calling dispose(). Disposing an engine while any session is
+        still alive violates the API contract; behavior is undefined.
+
+        This method is idempotent and safe to call multiple times.
+        It never raises exceptions (catches and logs internally).
+        After dispose(), all methods except dispose() raise EngineError.
+        """
+        ...

abogen/tts_plugin/errors.py

@@ -0,0 +1,62 @@
+"""Error hierarchy for the TTS Plugin Architecture.
+
+This module defines typed exceptions that engines raise.
+Engines should never raise raw exceptions; they must use EngineError or its subtypes.
+"""
+
+from __future__ import annotations
+
+
+class EngineError(Exception):
+    """Base exception for all engine errors.
+
+    All engine operations that can fail should raise EngineError or one of its subtypes.
+    After dispose(), all methods except dispose() raise EngineError.
+    """
+
+    pass
+
+
+class ModelNotFoundError(EngineError):
+    """Raised when a required model is not found."""
+
+    pass
+
+
+class ModelLoadError(EngineError):
+    """Raised when a model fails to load."""
+
+    pass
+
+
+class NetworkError(EngineError):
+    """Raised when a network operation fails."""
+
+    pass
+
+
+class InvalidInputError(EngineError):
+    """Raised when invalid input is provided to the engine."""
+
+    pass
+
+
+class ConfigurationError(EngineError):
+    """Raised when there is a configuration error."""
+
+    pass
+
+
+class CancelledError(EngineError):
+    """Raised when an operation is cancelled.
+
+    This is raised by synthesize() when cancel() is called during synthesis.
+    """
+
+    pass
+
+
+class InternalError(EngineError):
+    """Raised when an internal engine error occurs."""
+
+    pass

abogen/tts_plugin/host_context.py

@@ -0,0 +1,46 @@
+"""Host context for the TTS Plugin Architecture.
+
+This module defines the HostContext dataclass that provides minimal
+host services to plugins. It is the only interface through which
+plugins can access host functionality.
+"""
+
+from __future__ import annotations
+
+import logging
+from dataclasses import dataclass
+from pathlib import Path
+from typing import Protocol, runtime_checkable
+
+
+@runtime_checkable
+class HttpClient(Protocol):
+    """Protocol for HTTP client provided by host.
+
+    Plugins can use this for network requests (e.g., API-based engines).
+    """
+
+    def get(self, url: str, **kwargs: object) -> object:
+        """Perform an HTTP GET request."""
+        ...
+
+    def post(self, url: str, **kwargs: object) -> object:
+        """Perform an HTTP POST request."""
+        ...
+
+
+@dataclass(frozen=True)
+class HostContext:
+    """Minimal host context provided to plugins.
+
+    Contains only essential host services. No business logic.
+
+    Attributes:
+        config_dir: Directory for API keys, preferences, and configuration.
+        logger: Logger for plugin logging.
+        http_client: HTTP client for network requests.
+    """
+
+    config_dir: Path
+    logger: logging.Logger
+    http_client: HttpClient

abogen/tts_plugin/loader.py

@@ -0,0 +1,365 @@
+"""Plugin loader infrastructure for the TTS Plugin Architecture.
+
+This module provides functionality to discover, import, validate, and load
+TTS plugins. It handles both valid and invalid plugins, providing diagnostic
+messages for errors.
+
+The loader does NOT:
+- Create Engine instances (that's the plugin's create_engine() responsibility)
+- Manage plugin lifecycle (that's the Plugin Manager's responsibility)
+- Implement any TTS engine functionality
+"""
+
+from __future__ import annotations
+
+import importlib
+import re
+import sys
+import types
+from dataclasses import dataclass, field
+from pathlib import Path
+from typing import Any, Callable
+
+from abogen.tts_plugin.manifest import ModelManifest, PluginManifest
+
+
+# Host API version for compatibility checking
+HOST_API_VERSION = "1.0"
+
+
+@dataclass(frozen=True)
+class PluginLoadError:
+    """Diagnostic information for a failed plugin load.
+
+    Attributes:
+        plugin_id: Plugin identifier if available, otherwise directory name.
+        path: Path to the plugin directory.
+        errors: List of error messages describing what went wrong.
+    """
+
+    plugin_id: str
+    path: Path
+    errors: tuple[str, ...] = field(default_factory=tuple)
+
+
+@dataclass(frozen=True)
+class PluginLoadResult:
+    """Result of loading a plugin.
+
+    Attributes:
+        success: Whether the plugin loaded successfully.
+        manifest: The plugin manifest if successful.
+        model_requirements: Model requirements if successful.
+        create_engine: The create_engine function if successful.
+        module: The plugin module if successful.
+        error: Error information if failed.
+    """
+
+    success: bool
+    manifest: PluginManifest | None = None
+    model_requirements: tuple[ModelManifest, ...] | None = None
+    create_engine: Callable[..., Any] | None = None
+    module: types.ModuleType | None = None
+    error: PluginLoadError | None = None
+
+
+def _parse_api_version(version: str) -> tuple[int, int] | None:
+    """Parse an api_version string into (major, minor) tuple.
+
+    Args:
+        version: Version string in format "MAJOR.MINOR".
+
+    Returns:
+        Tuple of (major, minor) or None if invalid format.
+    """
+    match = re.match(r"^(\d+)\.(\d+)$", version)
+    if match:
+        return int(match.group(1)), int(match.group(2))
+    return None
+
+
+def _check_api_version_compatibility(plugin_version: str) -> str | None:
+    """Check if plugin api_version is compatible with host.
+
+    Architecture spec:
+    - Format: semver (MAJOR.MINOR)
+    - Compatibility: Host rejects plugin if major version differs
+    - Minor version: backward compatible, Host accepts higher minor
+
+    Args:
+        plugin_version: Plugin's api_version string.
+
+    Returns:
+        Error message if incompatible, None if compatible.
+    """
+    plugin_ver = _parse_api_version(plugin_version)
+    if plugin_ver is None:
+        return f"Invalid api_version format: '{plugin_version}'. Expected format: MAJOR.MINOR"
+
+    host_ver = _parse_api_version(HOST_API_VERSION)
+    if host_ver is None:
+        return f"Invalid host api_version format: '{HOST_API_VERSION}'"
+
+    if plugin_ver[0] != host_ver[0]:
+        return (
+            f"api_version major mismatch: plugin={plugin_ver[0]}, host={host_ver[0]}. "
+            f"Major version must match for compatibility."
+        )
+
+    return None
+
+
+def _validate_manifest(module: types.ModuleType, plugin_dir: Path) -> list[str]:
+    """Validate that a plugin module has required exports.
+
+    Args:
+        module: The imported plugin module.
+        plugin_dir: Path to the plugin directory.
+
+    Returns:
+        List of error messages (empty if valid).
+    """
+    errors: list[str] = []
+
+    # Check PLUGIN_MANIFEST
+    manifest = getattr(module, "PLUGIN_MANIFEST", None)
+    if manifest is None:
+        errors.append("Missing PLUGIN_MANIFEST export")
+    elif not isinstance(manifest, PluginManifest):
+        errors.append(
+            f"PLUGIN_MANIFEST must be a PluginManifest instance, "
+            f"got {type(manifest).__name__}"
+        )
+
+    # Check MODEL_REQUIREMENTS
+    model_reqs = getattr(module, "MODEL_REQUIREMENTS", None)
+    if model_reqs is None:
+        errors.append("Missing MODEL_REQUIREMENTS export")
+    elif not isinstance(model_reqs, list):
+        errors.append(
+            f"MODEL_REQUIREMENTS must be a list, got {type(model_reqs).__name__}"
+        )
+    else:
+        for i, req in enumerate(model_reqs):
+            if not isinstance(req, ModelManifest):
+                errors.append(
+                    f"MODEL_REQUIREMENTS[{i}] must be a ModelManifest instance, "
+                    f"got {type(req).__name__}"
+                )
+
+    # Check create_engine
+    create_engine = getattr(module, "create_engine", None)
+    if create_engine is None:
+        errors.append("Missing create_engine export")
+    elif not callable(create_engine):
+        errors.append(
+            f"create_engine must be callable, got {type(create_engine).__name__}"
+        )
+
+    return errors
+
+
+def _validate_capabilities(manifest: PluginManifest) -> list[str]:
+    """Validate plugin capabilities.
+
+    Args:
+        manifest: The plugin manifest to validate.
+
+    Returns:
+        List of error messages (empty if valid).
+    """
+    errors: list[str] = []
+
+    # Known capabilities (can be extended)
+    known_capabilities = frozenset({
+        "voice_list",
+        "preview",
+        "voice_clone",
+        "voice_blend",
+        "streaming",
+        "cancel",
+    })
+
+    for cap in manifest.capabilities:
+        if cap not in known_capabilities:
+            errors.append(f"Unknown capability: '{cap}'")
+
+    return errors
+
+
+def _validate_api_version(manifest: PluginManifest) -> list[str]:
+    """Validate api_version compatibility.
+
+    Args:
+        manifest: The plugin manifest to validate.
+
+    Returns:
+        List of error messages (empty if valid).
+    """
+    errors: list[str] = []
+    error = _check_api_version_compatibility(manifest.api_version)
+    if error:
+        errors.append(error)
+    return errors
+
+
+def load_plugin_from_dir(plugin_dir: Path) -> PluginLoadResult:
+    """Load and validate a plugin from a directory.
+
+    The plugin directory must contain an __init__.py that exports:
+    - PLUGIN_MANIFEST: PluginManifest
+    - MODEL_REQUIREMENTS: list[ModelManifest]
+    - create_engine: Callable
+
+    Args:
+        plugin_dir: Path to the plugin directory.
+
+    Returns:
+        PluginLoadResult with success status and either plugin data or error info.
+    """
+    plugin_id = plugin_dir.name
+    errors: list[str] = []
+
+    # Check if directory exists
+    if not plugin_dir.exists():
+        return PluginLoadResult(
+            success=False,
+            error=PluginLoadError(
+                plugin_id=plugin_id,
+                path=plugin_dir,
+                errors=(f"Plugin directory does not exist: {plugin_dir}",),
+            ),
+        )
+
+    # Check for __init__.py
+    init_file = plugin_dir / "__init__.py"
+    if not init_file.exists():
+        return PluginLoadResult(
+            success=False,
+            error=PluginLoadError(
+                plugin_id=plugin_id,
+                path=plugin_dir,
+                errors=("Missing __init__.py in plugin directory",),
+            ),
+        )
+
+    # Import the module
+    module_name = f"abogen.tts_plugin._loaded.{plugin_id}"
+    try:
+        # Remove from cache if already imported (for testing)
+        if module_name in sys.modules:
+            del sys.modules[module_name]
+
+        spec = importlib.util.spec_from_file_location(
+            module_name, init_file, submodule_search_locations=[]
+        )
+        if spec is None or spec.loader is None:
+            return PluginLoadResult(
+                success=False,
+                error=PluginLoadError(
+                    plugin_id=plugin_id,
+                    path=plugin_dir,
+                    errors=(f"Failed to create module spec for {init_file}",),
+                ),
+            )
+
+        module = importlib.util.module_from_spec(spec)
+        sys.modules[module_name] = module
+        spec.loader.exec_module(module)
+    except Exception as e:
+        # Clean up module from sys.modules on import failure
+        if module_name in sys.modules:
+            del sys.modules[module_name]
+        return PluginLoadResult(
+            success=False,
+            error=PluginLoadError(
+                plugin_id=plugin_id,
+                path=plugin_dir,
+                errors=(f"Failed to import plugin module: {e}",),
+            ),
+        )
+
+    # Validate manifest
+    manifest_errors = _validate_manifest(module, plugin_dir)
+    errors.extend(manifest_errors)
+
+    # If manifest is valid, perform additional validation
+    manifest = getattr(module, "PLUGIN_MANIFEST", None)
+    if isinstance(manifest, PluginManifest):
+        # Validate api_version
+        api_errors = _validate_api_version(manifest)
+        errors.extend(api_errors)
+
+        # Validate capabilities
+        cap_errors = _validate_capabilities(manifest)
+        errors.extend(cap_errors)
+
+        # Use manifest id if available
+        plugin_id = manifest.id
+
+    # Check if any errors occurred
+    if errors:
+        # Clean up module from sys.modules
+        if module_name in sys.modules:
+            del sys.modules[module_name]
+
+        return PluginLoadResult(
+            success=False,
+            error=PluginLoadError(
+                plugin_id=plugin_id,
+                path=plugin_dir,
+                errors=tuple(errors),
+            ),
+        )
+
+    # Get MODEL_REQUIREMENTS
+    model_requirements = tuple(getattr(module, "MODEL_REQUIREMENTS", []))
+    create_engine = getattr(module, "create_engine", None)
+
+    return PluginLoadResult(
+        success=True,
+        manifest=manifest,
+        model_requirements=model_requirements,
+        create_engine=create_engine,
+        module=module,
+    )
+
+
+def discover_plugins(plugin_dirs: list[Path]) -> list[PluginLoadResult]:
+    """Discover and load plugins from multiple directories.
+
+    Args:
+        plugin_dirs: List of directories to scan for plugins.
+
+    Returns:
+        List of PluginLoadResult, one per plugin directory found.
+    """
+    results: list[PluginLoadResult] = []
+
+    for plugin_dir in plugin_dirs:
+        if not plugin_dir.exists():
+            continue
+
+        # Scan for subdirectories (each is a potential plugin)
+        for item in sorted(plugin_dir.iterdir()):
+            if item.is_dir() and not item.name.startswith("."):
+                result = load_plugin_from_dir(item)
+                results.append(result)
+
+    return results
+
+
+def load_plugin(
+    plugin_dir: Path,
+) -> PluginLoadResult:
+    """Load a single plugin from a directory.
+
+    This is the main entry point for loading a plugin.
+
+    Args:
+        plugin_dir: Path to the plugin directory.
+
+    Returns:
+        PluginLoadResult with success status and either plugin data or error info.
+    """
+    return load_plugin_from_dir(plugin_dir)

abogen/tts_plugin/manifest.py

@@ -0,0 +1,189 @@
+"""Plugin manifest types for the TTS Plugin Architecture.
+
+This module contains static metadata types that describe plugins.
+These types have no dependencies and are immutable.
+"""
+
+from __future__ import annotations
+
+from dataclasses import dataclass, field
+from typing import Any
+
+
+@dataclass(frozen=True)
+class AudioFormatManifest:
+    """Manifest describing an audio format.
+
+    Attributes:
+        mime: MIME type of the audio.
+        extension: File extension.
+    """
+
+    mime: str
+    extension: str
+
+
+@dataclass(frozen=True)
+class EnumOption:
+    """Manifest describing an enum option for a parameter.
+
+    Attributes:
+        value: The enum value.
+        label: Human-readable label.
+    """
+
+    value: str
+    label: str
+
+
+@dataclass(frozen=True)
+class ParameterManifest:
+    """Manifest describing a synthesis parameter.
+
+    Attributes:
+        id: Parameter identifier.
+        name: Human-readable name.
+        description: Parameter description.
+        type: Parameter type ("float", "int", "string", "boolean", "enum").
+        default: Default value.
+        min: Minimum value (optional, for numeric types).
+        max: Maximum value (optional, for numeric types).
+        step: Step size (optional, for numeric types).
+        options: Available options (optional, for enum type).
+        unit: Unit of measurement (optional).
+        group: Parameter group (optional).
+    """
+
+    id: str
+    name: str
+    description: str
+    type: str
+    default: Any
+    min: float | None = None
+    max: float | None = None
+    step: float | None = None
+    options: tuple[EnumOption, ...] = field(default_factory=tuple)
+    unit: str | None = None
+    group: str | None = None
+
+
+@dataclass(frozen=True)
+class VoiceManifest:
+    """Manifest describing a voice.
+
+    Attributes:
+        id: Voice identifier.
+        name: Human-readable name.
+        tags: Voice tags (e.g., language, style).
+    """
+
+    id: str
+    name: str
+    tags: tuple[str, ...] = field(default_factory=tuple)
+
+
+@dataclass(frozen=True)
+class VoiceSourceManifest:
+    """Manifest describing a voice source.
+
+    Attributes:
+        id: Voice source identifier.
+        name: Human-readable name.
+        type: Source type ("list", "speaker_id", "clone", "blend", "generate", "none").
+        config: Source-specific configuration.
+    """
+
+    id: str
+    name: str
+    type: str
+    config: Any = None
+
+
+@dataclass(frozen=True)
+class EngineManifest:
+    """Manifest describing engine capabilities.
+
+    Attributes:
+        voiceSources: Available voice sources.
+        parameters: Available synthesis parameters.
+        audioFormats: Supported audio formats.
+    """
+
+    voiceSources: tuple[VoiceSourceManifest, ...] = field(default_factory=tuple)
+    parameters: tuple[ParameterManifest, ...] = field(default_factory=tuple)
+    audioFormats: tuple[AudioFormatManifest, ...] = field(default_factory=tuple)
+
+
+@dataclass(frozen=True)
+class GpuRequirement:
+    """Manifest describing GPU requirements.
+
+    Attributes:
+        required: Whether GPU is required.
+        type: GPU type (e.g., "cuda", "rocm").
+        memory: Required GPU memory in GB.
+    """
+
+    required: bool = False
+    type: str | None = None
+    memory: float | None = None
+
+
+@dataclass(frozen=True)
+class RequirementManifest:
+    """Manifest describing plugin requirements.
+
+    Attributes:
+        gpu: GPU requirements (optional).
+        memory: Required RAM in GB (optional).
+        internet: Whether internet is required (optional).
+    """
+
+    gpu: GpuRequirement | None = None
+    memory: float | None = None
+    internet: bool | None = None
+
+
+@dataclass(frozen=True)
+class ModelManifest:
+    """Manifest describing a model requirement.
+
+    Attributes:
+        id: Model identifier.
+        name: Human-readable name.
+        size: Model size as string (e.g., "100MB", "2GB").
+    """
+
+    id: str
+    name: str
+    size: str
+
+
+@dataclass(frozen=True)
+class PluginManifest:
+    """Main manifest for a TTS plugin.
+
+    Attributes:
+        id: Plugin identifier (unique).
+        name: Human-readable name.
+        version: Plugin version.
+        api_version: API version (semver format: MAJOR.MINOR).
+        description: Plugin description.
+        author: Plugin author.
+        capabilities: List of capability identifiers.
+        requires: Plugin requirements.
+        engine: Engine manifest.
+        voices: Optional static voice catalog. None = not declared (use VoiceLister),
+            empty tuple = explicitly no static voices, non-empty = static catalog.
+    """
+
+    id: str
+    name: str
+    version: str
+    api_version: str
+    description: str
+    author: str
+    capabilities: tuple[str, ...] = field(default_factory=tuple)
+    requires: RequirementManifest = field(default_factory=RequirementManifest)
+    engine: EngineManifest = field(default_factory=EngineManifest)
+    voices: tuple[VoiceManifest, ...] | None = None

abogen/tts_plugin/plugin.py

@@ -0,0 +1,55 @@
+"""Plugin contract for the TTS Plugin Architecture.
+
+This module defines the plugin contract that all TTS plugins must implement.
+Each plugin must export:
+- PLUGIN_MANIFEST: PluginManifest instance
+- MODEL_REQUIREMENTS: list of ModelManifest instances
+- create_engine(): Factory function that creates an Engine
+
+The create_engine() function is the entry point for plugin activation.
+It must be atomic: succeed fully or raise and clean up.
+"""
+
+from __future__ import annotations
+
+from pathlib import Path
+from typing import Protocol, runtime_checkable
+
+from abogen.tts_plugin.engine import Engine
+from abogen.tts_plugin.host_context import HostContext
+from abogen.tts_plugin.types import EngineConfig
+
+
+@runtime_checkable
+class Plugin(Protocol):
+    """Protocol defining the plugin contract.
+
+    Every TTS plugin must implement this protocol by exporting:
+    - PLUGIN_MANIFEST: PluginManifest
+    - MODEL_REQUIREMENTS: list[ModelManifest]
+    - create_engine: Callable[[HostContext, Path | None, EngineConfig], Engine]
+    """
+
+    def create_engine(
+        self,
+        context: HostContext,
+        model_path: Path | None,
+        config: EngineConfig,
+    ) -> Engine:
+        """Create an engine instance.
+
+        This is the factory function that creates an Engine from a plugin.
+        It must be atomic: succeed fully or raise EngineError and clean up.
+
+        Args:
+            context: Host services (config dir, logger, http client).
+            model_path: Resolved model path, or None for cloud/no-model engines.
+            config: Engine initialization settings.
+
+        Returns:
+            A fully initialized Engine instance.
+
+        Raises:
+            EngineError: On failure. Cleans up partially created resources.
+        """
+        ...

abogen/tts_plugin/plugin_manager.py

@@ -0,0 +1,153 @@
+"""Plugin Manager
+
+Provides a simple interface for consumers to access TTS engines via the
+new Plugin Architecture. Discovers, loads, and manages plugins from the
+plugins directory.
+
+Usage:
+    from abogen.tts_plugin.plugin_manager import get_plugin_manager
+
+    manager = get_plugin_manager()
+    engine = manager.create_engine("kokoro", lang_code="a", device="cpu")
+    session = engine.create_session()
+    try:
+        result = session.synthesize("Hello world")
+    finally:
+        session.dispose()
+"""
+
+from typing import Any, Dict, List, Optional, Type
+
+from abogen.tts_plugin.engine import Engine, EngineSession
+from abogen.tts_plugin.manifest import PluginManifest
+from abogen.tts_plugin.types import AudioFormat
+
+
+class PluginManager:
+    """Manages TTS plugins and provides a simple interface for consumers."""
+
+    def __init__(self) -> None:
+        self._plugins: Dict[str, dict] = {}
+        self._engines: Dict[str, Engine] = {}
+        self._loaded = False
+
+    def discover(self, plugins_dir: str = "plugins") -> None:
+        """Discover and load all plugins from the given directory."""
+        import os
+        from pathlib import Path
+        from abogen.tts_plugin.loader import load_plugin_from_dir
+
+        self._plugins.clear()
+        self._engines.clear()
+
+        plugins_path = Path(plugins_dir)
+        if not plugins_path.exists():
+            self._loaded = True
+            return
+
+        for entry in plugins_path.iterdir():
+            if entry.is_dir() and (entry / "__init__.py").exists():
+                try:
+                    result = load_plugin_from_dir(entry)
+                    if result.success and result.manifest is not None:
+                        self._plugins[result.manifest.id] = {
+                            "manifest": result.manifest,
+                            "create_engine": result.create_engine,
+                            "module": result.module,
+                        }
+                except Exception as e:
+                    # Log error but continue with other plugins
+                    print(f"Warning: Failed to load plugin from {entry}: {e}")
+
+        self._loaded = True
+
+    def _ensure_loaded(self) -> None:
+        """Ensure plugins have been discovered."""
+        if not self._loaded:
+            self.discover()
+
+    def list_plugins(self) -> List[PluginManifest]:
+        """Return manifests for all loaded plugins."""
+        self._ensure_loaded()
+        return [info["manifest"] for info in self._plugins.values()]
+
+    def get_plugin(self, plugin_id: str) -> Optional[dict]:
+        """Get plugin info by ID."""
+        self._ensure_loaded()
+        return self._plugins.get(plugin_id)
+
+    def has_plugin(self, plugin_id: str) -> bool:
+        """Check if a plugin is loaded."""
+        self._ensure_loaded()
+        return plugin_id in self._plugins
+
+    def create_engine(self, plugin_id: str, **kwargs: Any) -> Engine:
+        """Create an engine instance for the given plugin.
+
+        Args:
+            plugin_id: The plugin identifier (e.g., "kokoro")
+            **kwargs: Arguments passed to the engine constructor
+
+        Returns:
+            An Engine instance
+
+        Raises:
+            KeyError: If plugin_id is not found
+            Exception: If engine creation fails
+        """
+        self._ensure_loaded()
+
+        if plugin_id not in self._plugins:
+            raise KeyError(f"Plugin not found: {plugin_id}")
+
+        plugin_info = self._plugins[plugin_id]
+        create_engine_func = plugin_info["create_engine"]
+
+        # Create engine using the plugin's factory
+        engine = create_engine_func(**kwargs)
+        return engine
+
+    def get_or_create_engine(self, plugin_id: str, **kwargs: Any) -> Engine:
+        """Get an existing engine or create a new one.
+
+        Engines are cached by plugin_id. If you need multiple instances
+        with different parameters, use create_engine() directly.
+        """
+        self._ensure_loaded()
+
+        cache_key = plugin_id
+        if cache_key in self._engines:
+            return self._engines[cache_key]
+
+        engine = self.create_engine(plugin_id, **kwargs)
+        self._engines[cache_key] = engine
+        return engine
+
+    def dispose_all(self) -> None:
+        """Dispose all cached engines."""
+        for engine in self._engines.values():
+            try:
+                engine.dispose()
+            except Exception:
+                pass  # dispose() should never raise
+        self._engines.clear()
+
+
+# Global singleton
+_manager: Optional[PluginManager] = None
+
+
+def get_plugin_manager() -> PluginManager:
+    """Get the global PluginManager instance."""
+    global _manager
+    if _manager is None:
+        _manager = PluginManager()
+    return _manager
+
+
+def reset_plugin_manager() -> None:
+    """Reset the global PluginManager (for testing)."""
+    global _manager
+    if _manager is not None:
+        _manager.dispose_all()
+    _manager = None

abogen/tts_plugin/types.py

@@ -0,0 +1,111 @@
+"""Core domain types for the TTS Plugin Architecture.
+
+This module contains immutable value objects that form the core domain.
+These types have zero dependencies and are used across the plugin system.
+"""
+
+from __future__ import annotations
+
+from dataclasses import dataclass, field
+from typing import Any, Mapping
+
+
+@dataclass(frozen=True)
+class AudioFormat:
+    """Immutable value object representing an audio format.
+
+    Attributes:
+        mime: MIME type of the audio (e.g., "audio/wav", "audio/mpeg").
+        extension: File extension (e.g., "wav", "mp3").
+    """
+
+    mime: str
+    extension: str
+
+
+@dataclass(frozen=True)
+class Duration:
+    """Immutable value object representing a time duration.
+
+    Attributes:
+        seconds: Duration in seconds.
+    """
+
+    seconds: float
+
+
+@dataclass(frozen=True)
+class VoiceSelection:
+    """Immutable value object for voice selection. Opaque to engine.
+
+    Attributes:
+        source: Voice source identifier (e.g., "builtin", "clone").
+        key: Voice key within the source.
+        payload: Optional payload for clone/blend sources.
+    """
+
+    source: str
+    key: str
+    payload: Any = None
+
+
+@dataclass(frozen=True)
+class ParameterValues:
+    """Immutable value object for synthesis parameters. Behaves like Mapping[str, Any].
+
+    Attributes:
+        values: Mapping of parameter names to their values.
+    """
+
+    values: Mapping[str, Any] = field(default_factory=dict)
+
+
+@dataclass(frozen=True)
+class SynthesisRequest:
+    """Immutable value object for a synthesis request.
+
+    Attributes:
+        text: Text to synthesize.
+        voice: Voice selection.
+        parameters: Synthesis parameters.
+        format: Desired audio output format.
+    """
+
+    text: str
+    voice: VoiceSelection
+    parameters: ParameterValues
+    format: AudioFormat
+
+
+@dataclass(frozen=True)
+class SynthesizedAudio:
+    """Immutable value object for synthesized audio result.
+
+    Attributes:
+        data: Raw audio bytes.
+        format: Audio format of the result.
+        duration: Duration of the audio.
+    """
+
+    data: bytes
+    format: AudioFormat
+    duration: Duration
+
+
+@dataclass(frozen=True)
+class EngineConfig:
+    """Immutable configuration of an Engine instance.
+
+    Contains parameters that define how a particular Engine instance is
+    created and that remain constant throughout the lifetime of that Engine.
+
+    Plugin implementations may ignore fields that are not applicable to them.
+
+    Attributes:
+        device: Device to use (e.g., "cpu", "cuda:0").
+        lang_code: Language code for the engine (e.g., "a" for Kokoro English).
+            Plugins that do not require a language code ignore this field.
+    """
+
+    device: str = "cpu"
+    lang_code: str = "a"

abogen/tts_plugin/utils.py

@@ -0,0 +1,235 @@
+"""TTS Plugin Architecture — direct utility functions.
+
+Provides helpers that replace the former compatibility adapter by
+calling the Plugin Manager directly.
+"""
+
+from __future__ import annotations
+
+from typing import Any, Iterator
+
+import numpy as np
+
+from abogen.tts_plugin.plugin_manager import get_plugin_manager
+
+
+def get_voices(plugin_id: str) -> tuple[str, ...]:
+    """Return the voice-id tuple for *plugin_id*.
+
+    Uses the official Plugin Architecture: PluginManager → Engine → VoiceLister.
+    First checks plugin manifest for static voice catalog.
+    """
+    import logging
+    import tempfile
+    from pathlib import Path
+
+    from abogen.tts_plugin.host_context import HostContext
+    from abogen.tts_plugin.types import EngineConfig
+
+    manager = get_plugin_manager()
+    if not manager.has_plugin(plugin_id):
+        return ()
+
+    # Check manifest for static voice catalog
+    plugin_info = manager.get_plugin(plugin_id)
+    if plugin_info is not None:
+        manifest = plugin_info.get("manifest")
+        if manifest is not None and manifest.voices is not None:
+            return tuple(v.id for v in manifest.voices)
+
+    ctx = HostContext(
+        config_dir=Path(tempfile.gettempdir()),
+        logger=logging.getLogger(f"abogen.utils.{plugin_id}"),
+        http_client=type("_StubHttpClient", (), {
+            "get": staticmethod(lambda url, **kw: None),
+            "post": staticmethod(lambda url, **kw: None),
+        })(),
+    )
+
+    try:
+        engine = manager.create_engine(
+            plugin_id,
+            context=ctx,
+            model_path=None,
+            config=EngineConfig(device="cpu"),
+        )
+    except Exception:
+        return ()
+
+    try:
+        from abogen.tts_plugin.capabilities import VoiceLister
+
+        if isinstance(engine, VoiceLister):
+            manifests = engine.listVoices("builtin")
+            return tuple(v.id for v in manifests)
+        return ()
+    except Exception:
+        return ()
+    finally:
+        engine.dispose()
+
+
+def get_default_voice(plugin_id: str, fallback: str = "") -> str:
+    """Return the first voice of *plugin_id*, or *fallback*."""
+    voices = get_voices(plugin_id)
+    return voices[0] if voices else fallback
+
+
+def is_plugin_registered(plugin_id: str) -> bool:
+    """Check whether *plugin_id* is loaded by the Plugin Manager."""
+    return get_plugin_manager().has_plugin(plugin_id)
+
+
+def resolve_voice_to_plugin(spec: str, fallback: str = "kokoro") -> str:
+    """Determine which plugin owns the given voice specification.
+
+    Resolution rules:
+    1. Empty spec -> fallback
+    2. Kokoro formula (contains '*' or '+') -> "kokoro"
+    3. Exact voice-id match against loaded plugins -> plugin id
+    4. Unknown voice -> fallback
+    """
+    raw = str(spec or "").strip()
+    if not raw:
+        return fallback
+
+    if "*" in raw or "+" in raw:
+        return "kokoro"
+
+    upper = raw.upper()
+    manager = get_plugin_manager()
+
+    for manifest in manager.list_plugins():
+        for voice_source in manifest.engine.voiceSources:
+            if voice_source.type == "list" and isinstance(voice_source.config, dict):
+                try:
+                    engine = manager.create_engine(manifest.id)
+                    try:
+                        if hasattr(engine, "listVoices"):
+                            voice_manifests = engine.listVoices(voice_source.id)
+                            voice_ids = [v.id.upper() for v in voice_manifests]
+                            if upper in voice_ids:
+                                return manifest.id
+                    finally:
+                        engine.dispose()
+                except Exception:
+                    continue
+
+    return fallback
+
+
+class Pipeline:
+    """Callable wrapper around Engine / EngineSession.
+
+    Presents the same interface that old callers expect::
+
+        pipeline = create_pipeline("kokoro", lang_code="a", device="cpu")
+        for segment in pipeline(text, voice="af_nova", speed=1.0):
+            audio = segment.audio
+    """
+
+    def __init__(self, engine: Any, **engine_kwargs: Any) -> None:
+        self._engine = engine
+        self._engine_kwargs = engine_kwargs
+        self._session: Any = None
+
+    def _ensure_session(self) -> Any:
+        if self._session is None:
+            self._session = self._engine.createSession()
+        return self._session
+
+    def __call__(
+        self,
+        text: str,
+        voice: str = "default",
+        speed: float = 1.0,
+        split_pattern: str | None = None,
+        **kwargs: Any,
+    ) -> Iterator[Any]:
+        from abogen.tts_plugin.types import (
+            AudioFormat,
+            ParameterValues,
+            SynthesisRequest,
+            VoiceSelection,
+        )
+
+        session = self._ensure_session()
+
+        params: dict[str, Any] = {"speed": speed}
+        if split_pattern is not None:
+            params["split_pattern"] = split_pattern
+        params.update(kwargs)
+
+        request = SynthesisRequest(
+            text=text,
+            voice=VoiceSelection(source="builtin", key=voice),
+            parameters=ParameterValues(values=params),
+            format=AudioFormat(mime="audio/wav", extension="wav"),
+        )
+
+        result = session.synthesize(request)
+        audio_array = np.frombuffer(result.data, dtype=np.float32)
+
+        from dataclasses import dataclass
+
+        @dataclass
+        class Segment:
+            graphemes: str
+            audio: np.ndarray
+
+        yield Segment(graphemes=text, audio=audio_array)
+
+    def dispose(self) -> None:
+        if self._session is not None:
+            try:
+                self._session.dispose()
+            except Exception:
+                pass
+            self._session = None
+
+    def __del__(self) -> None:
+        self.dispose()
+
+
+def create_pipeline(
+    plugin_id: str,
+    *,
+    lang_code: str = "a",
+    device: str = "cpu",
+) -> Pipeline:
+    """Create a callable TTS pipeline via the Plugin Architecture.
+
+    Builds a proper HostContext and EngineConfig, then delegates to the
+    PluginManager to create the engine. Returns a :class:`Pipeline` whose
+    ``__call__`` interface matches the callable protocol used by consumers.
+
+    Args:
+        plugin_id: Plugin identifier (e.g., "kokoro", "supertonic").
+        lang_code: Language code for the engine.
+        device: Device to use (e.g., "cpu", "cuda:0").
+
+    Returns:
+        A callable Pipeline instance.
+    """
+    import logging
+    import tempfile
+    from pathlib import Path
+
+    from abogen.tts_plugin.host_context import HostContext
+    from abogen.tts_plugin.types import EngineConfig
+
+    manager = get_plugin_manager()
+
+    ctx = HostContext(
+        config_dir=Path(tempfile.gettempdir()),
+        logger=logging.getLogger(f"abogen.pipeline.{plugin_id}"),
+        http_client=type("_StubHttpClient", (), {
+            "get": staticmethod(lambda url, **kw: None),
+            "post": staticmethod(lambda url, **kw: None),
+        })(),
+    )
+
+    config = EngineConfig(device=device, lang_code=lang_code)
+
+    engine = manager.create_engine(plugin_id, context=ctx, model_path=None, config=config)
+    return Pipeline(engine)

abogen/utils.py

@@ -529,21 +529,20 @@ def prevent_sleep_end():
                 _sleep_procs[system] = None
 
 
-def load_numpy_kpipeline():
-    import numpy as np
-    from kokoro import KPipeline  # type: ignore[import-not-found]
-
-    return np, KPipeline
-
-
 class LoadPipelineThread(Thread):
-    def __init__(self, callback):
+    def __init__(self, callback, lang_code="a", use_gpu=True):
         super().__init__()
         self.callback = callback
+        self.lang_code = lang_code
+        self.use_gpu = use_gpu
 
     def run(self):
         try:
-            np_module, kpipeline_class = load_numpy_kpipeline()
+            from abogen.domain.pipeline_factory import create_pipeline_for_job
-            self.callback(np_module, kpipeline_class, None)
+
+            backend = create_pipeline_for_job(
+                "kokoro", language=self.lang_code, use_gpu=self.use_gpu
+            )
+            self.callback(backend, None)
         except Exception as e:
-            self.callback(None, None, str(e))
+            self.callback(None, str(e))

abogen/voice_cache.py

@@ -17,7 +17,7 @@ if LocalEntryNotFoundError is None:  # pragma: no cover - fallback for tests
         pass
 
 
-from abogen.constants import VOICES_INTERNAL
+from abogen.tts_plugin.utils import get_voices
 
 _CACHE_LOCK = threading.Lock()
 _CACHED_VOICES: Set[str] = set()
@@ -26,8 +26,9 @@ _BOOTSTRAPPED = False
 
 
 def _normalize_targets(voices: Optional[Iterable[str]]) -> Set[str]:
+    kokoro_voices = get_voices("kokoro")
     if not voices:
-        return set(VOICES_INTERNAL)
+        return set(kokoro_voices)
     normalized: Set[str] = set()
     for voice in voices:
         if not voice:
@@ -35,7 +36,7 @@ def _normalize_targets(voices: Optional[Iterable[str]]) -> Set[str]:
         voice_id = str(voice).strip()
         if not voice_id:
             continue
-        if voice_id in VOICES_INTERNAL:
+        if voice_id in kokoro_voices:
             normalized.add(voice_id)
     return normalized
 
@@ -143,3 +144,11 @@ def _ensure_single_voice_asset(
 
     hf_hub_download(resume_download=True, **common_kwargs)
     return True
+
+
+def clear_voice_cache() -> None:
+    """Clear the in‑process voice cache (used during shutdown)."""
+    with _CACHE_LOCK:
+        _CACHED_VOICES.clear()
+    global _BOOTSTRAPPED
+    _BOOTSTRAPPED = False

abogen/voice_formulas.py

@@ -1,7 +1,7 @@
 import re
-from typing import List, Tuple
+from typing import Iterable, List, Optional, Tuple
 
-from abogen.constants import VOICES_INTERNAL
+from abogen.tts_plugin.utils import get_voices
 
 
 # Calls parsing and loads the voice to gpu or cpu
@@ -22,6 +22,7 @@ def parse_formula_terms(formula: str) -> List[Tuple[str, float]]:
         raise ValueError("Empty voice formula")
 
     terms: List[Tuple[str, float]] = []
+    kokoro_voices = get_voices("kokoro")
     for segment in formula.split("+"):
         part = segment.strip()
         if not part:
@@ -30,7 +31,7 @@ def parse_formula_terms(formula: str) -> List[Tuple[str, float]]:
             raise ValueError("Each component must be in the form voice*weight")
         voice_name, raw_weight = part.split("*", 1)
         voice_name = voice_name.strip()
-        if voice_name not in VOICES_INTERNAL:
+        if voice_name not in kokoro_voices:
             raise ValueError(f"Unknown voice: {voice_name}")
         try:
             weight = float(raw_weight.strip())
@@ -71,6 +72,33 @@ def parse_voice_formula(pipeline, formula):
     return weighted_sum
 
 
+def pairs_to_formula(pairs: Iterable[Tuple[str, float]]) -> Optional[str]:
+    """Build a voice formula string from (voice_name, weight) pairs.
+
+    Normalizes weights to sum to 1.0 and formats as "voice1*0.5+voice2*0.5".
+
+    Args:
+        pairs: Iterable of (voice_name, weight) tuples. Zero-weight entries
+            are filtered out.
+
+    Returns:
+        Formula string, or None if no valid entries.
+    """
+    voices = [(voice, float(weight)) for voice, weight in pairs if weight is not None and float(weight) > 0]
+    if not voices:
+        return None
+    total = sum(weight for _, weight in voices)
+    if total <= 0:
+        return None
+
+    def _format_value(value: float) -> str:
+        normalized = value / total if total else 0.0
+        return (f"{normalized:.4f}").rstrip("0").rstrip(".") or "0"
+
+    parts = [f"{voice}*{_format_value(weight)}" for voice, weight in voices]
+    return "+".join(parts)
+
+
 def calculate_sum_from_formula(formula):
     weights = re.findall(r"\* *([\d.]+)", formula)
     total_sum = sum(float(weight) for weight in weights)

abogen/voice_metadata.py

@@ -0,0 +1,33 @@
+from dataclasses import dataclass
+
+
+@dataclass(frozen=True)
+class VoiceMetadata:
+    """
+    Immutable metadata describing a voice from a TTS backend.
+
+    This model describes a voice independently of any backend implementation.
+    Backends populate these objects; the application consumes them.
+
+    The ``backend_id`` field is set by the backend itself (via
+    ``self.metadata.id``) — the application never hardcodes it.
+    This ensures renaming a backend does not require touching voice definitions.
+    """
+
+    id: str
+    """Unique voice identifier within the backend (e.g. ``"af_alloy"``, ``"M1"``)."""
+
+    display_name: str
+    """Human-readable display name (e.g. ``"Alloy"``, ``"Male 1"``)."""
+
+    language: str
+    """Language code — backend-specific format is acceptable (e.g. ``"a"``, ``"en"``)."""
+
+    gender: str
+    """Gender category: ``"female"``, ``"male"``, or ``"unknown"``."""
+
+    backend_id: str
+    """Identifier of the backend that owns this voice (e.g. ``"kokoro"``).
+
+    Set automatically by the backend — never hardcoded in voice definitions.
+    """

abogen/voice_profiles.py

@@ -2,8 +2,7 @@ import json
 import os
 from typing import Any, Dict, Iterable, List, Tuple
 
-from abogen.constants import VOICES_INTERNAL
+from abogen.tts_plugin.utils import get_voices, is_plugin_registered
-from abogen.tts_supertonic import DEFAULT_SUPERTONIC_VOICES
 from abogen.utils import get_user_config_path
 
 
@@ -70,7 +69,8 @@ def serialize_profiles() -> Dict[str, Dict[str, Iterable[Tuple[str, float]]]]:
 
 def _normalize_supertonic_voice(value: Any) -> str:
     raw = str(value or "").strip().upper()
-    return raw if raw in DEFAULT_SUPERTONIC_VOICES else "M1"
+    supertonic_voices = get_voices("supertonic")
+    return raw if raw in supertonic_voices else "M1"
 
 
 def _coerce_supertonic_steps(value: Any) -> int:
@@ -101,7 +101,7 @@ def normalize_profile_entry(entry: Any) -> Dict[str, Any]:
         return {}
 
     provider = str(entry.get("provider") or "kokoro").strip().lower()
-    if provider not in {"kokoro", "supertonic"}:
+    if not is_plugin_registered(provider):
         provider = "kokoro"
 
     language = str(entry.get("language") or "a").strip().lower() or "a"
@@ -135,6 +135,7 @@ def normalize_profile_entry(entry: Any) -> Dict[str, Any]:
 
 def _normalize_voice_entries(entries: Iterable) -> List[Tuple[str, float]]:
     normalized: List[Tuple[str, float]] = []
+    kokoro_voices = get_voices("kokoro")
     for item in entries or []:
         if isinstance(item, dict):
             voice = item.get("id") or item.get("voice")
@@ -143,7 +144,7 @@ def _normalize_voice_entries(entries: Iterable) -> List[Tuple[str, float]]:
             voice, weight = item[0], item[1]
         else:
             continue
-        if voice not in VOICES_INTERNAL:
+        if voice not in kokoro_voices:
             continue
         if weight is None:
             continue

abogen/webui/Dockerfile

@@ -2,7 +2,6 @@ FROM nvidia/cuda:12.6.3-cudnn-runtime-ubuntu22.04
 
 ENV PYTHONDONTWRITEBYTECODE=1 \
   PYTHONUNBUFFERED=1 \
-  PIP_NO_CACHE_DIR=1 \
   VIRTUAL_ENV=/opt/venv \
   PATH=/opt/venv/bin:$PATH
 
@@ -27,22 +26,22 @@ RUN python3 -m venv "$VIRTUAL_ENV"
 WORKDIR /app
 
 COPY pyproject.toml README.md ./
-COPY abogen ./abogen
+RUN pip install uv \
-
-RUN pip install --upgrade pip \
   && if [ -n "$TORCH_VERSION" ]; then \
-       pip install torch=="$TORCH_VERSION" torchvision=="$TORCH_VERSION" torchaudio=="$TORCH_VERSION" --index-url "$TORCH_INDEX_URL"; \
+       uv pip install --system torch=="$TORCH_VERSION" torchvision=="$TORCH_VERSION" torchaudio=="$TORCH_VERSION" --index-url "$TORCH_INDEX_URL"; \
      else \
-       pip install torch torchvision torchaudio --index-url "$TORCH_INDEX_URL"; \
+       uv pip install --system torch torchvision torchaudio --index-url "$TORCH_INDEX_URL"; \
      fi \
-  && pip install --no-cache-dir . \
+  && uv pip install --system . \
     https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-3.8.0/en_core_web_sm-3.8.0-py3-none-any.whl \
-  && pip install --no-cache-dir "mutagen>=1.47.0"
+  && uv pip install --system "mutagen>=1.47.0"
+
+COPY abogen ./abogen
 
 # Install onnxruntime-gpu for CUDA acceleration (supertonic uses ONNX Runtime)
 # Set USE_GPU=false to skip this for CPU-only deployments
 RUN if [ "$USE_GPU" = "true" ]; then \
-      pip install --no-cache-dir onnxruntime-gpu; \
+      uv pip install --system onnxruntime-gpu; \
     fi
 
 ENV ABOGEN_HOST=0.0.0.0 \

abogen/webui/app.py

@@ -1,6 +1,5 @@
 from __future__ import annotations
 
-import atexit
 import logging
 import os
 from pathlib import Path
@@ -8,6 +7,8 @@ from typing import Any, Optional
 
 from flask import Flask
 
+from abogen import shutdown  # noqa: F401
+shutdown.register_shutdown()
 from abogen.utils import get_user_cache_path, get_user_output_path, get_user_settings_dir
 
 from .conversion_runner import run_conversion_job
@@ -83,6 +84,12 @@ def create_app(config: Optional[dict[str, Any]] = None) -> Flask:
         "UPLOAD_FOLDER": str(uploads_dir),
         "OUTPUT_FOLDER": str(outputs_dir),
         "MAX_CONTENT_LENGTH": 1024 * 1024 * 400,  # 400 MB uploads
+        # Large books can submit four form fields per chapter. Werkzeug's
+        # defaults reject those requests before the wizard route can process
+        # them, even though the encoded payload is much smaller than the upload
+        # limit above.
+        "MAX_FORM_MEMORY_SIZE": 10 * 1024 * 1024,
+        "MAX_FORM_PARTS": 10_000,
     }
     if config:
         base_config.update(config)
@@ -113,8 +120,6 @@ def create_app(config: Optional[dict[str, Any]] = None) -> Flask:
     app.register_blueprint(books_bp, url_prefix="/find-books")
     app.register_blueprint(api_bp, url_prefix="/api")
 
-    atexit.register(service.shutdown)
-
     global _access_log_filter_attached
     if not _access_log_filter_attached:
         logging.getLogger("werkzeug").addFilter(_SuppressSuccessfulAccessFilter())

abogen/webui/debug_tts_runner.py

@@ -14,8 +14,10 @@ from abogen.kokoro_text_normalization import normalize_for_pipeline
 from abogen.normalization_settings import build_apostrophe_config
 from abogen.text_extractor import extract_from_path
 from abogen.voice_cache import ensure_voice_assets
-from abogen.webui.conversion_runner import SAMPLE_RATE, SPLIT_PATTERN, _select_device, _to_float32, _resolve_voice, _spec_to_voice_ids
+from abogen.webui.conversion_runner import SAMPLE_RATE, _select_device, _to_float32, _spec_to_voice_ids
-from abogen.utils import load_numpy_kpipeline
+from abogen.domain.voice_loader import resolve_voice
+from abogen.domain.split_pattern import get_split_pattern
+from abogen.tts_plugin.utils import create_pipeline
 
 
 _MARKER_RE = re.compile(re.escape(MARKER_PREFIX) + r"(?P<code>[A-Z0-9_]+)" + re.escape(MARKER_SUFFIX))
@@ -45,8 +47,7 @@ def _load_pipeline(language: str, use_gpu: bool) -> Any:
     device = "cpu"
     if use_gpu:
         device = _select_device()
-    _np, KPipeline = load_numpy_kpipeline()
+    return create_pipeline("kokoro", lang_code=language, device=device)
-    return KPipeline(lang_code=language, repo_id="hexgrad/Kokoro-82M", device=device)
 
 
 def _extract_cases_from_text(text: str) -> List[Tuple[str, str]]:
@@ -176,7 +177,7 @@ def run_debug_tts_wavs(
             pass
 
     pipeline = _load_pipeline(language, use_gpu)
-    voice_choice = _resolve_voice(pipeline, voice_spec, use_gpu)
+    voice_choice = resolve_voice(voice_spec, pipeline, use_gpu)
 
     apostrophe_config = build_apostrophe_config(settings=settings)
     normalization_settings = dict(settings)
@@ -201,7 +202,7 @@ def run_debug_tts_wavs(
             normalized,
             voice=voice_choice,
             speed=speed,
-            split_pattern=SPLIT_PATTERN,
+            split_pattern=get_split_pattern(language, "Disabled"),
         ):
             audio = _to_float32(getattr(segment, "audio", None))
             if audio.size:
@@ -248,4 +249,8 @@ def run_debug_tts_wavs(
         "sample_rate": SAMPLE_RATE,
     }
     (run_dir / "manifest.json").write_text(json.dumps(manifest, indent=2), encoding="utf-8")
+    try:
+        pipeline.dispose()
+    except Exception:
+        pass
     return manifest

abogen/webui/routes/api.py

@@ -25,7 +25,7 @@ from abogen.voice_profiles import (
     normalize_profile_entry,
 )
 from abogen.webui.routes.utils.common import split_profile_spec
-from abogen.webui.routes.utils.preview import synthesize_preview, generate_preview_audio
+from abogen.webui.routes.utils.synthesize import synthesize_preview, generate_preview_audio
 from abogen.webui.routes.utils.voice import formula_from_profile
 from abogen.normalization_settings import (
     build_llm_configuration,
@@ -34,6 +34,7 @@ from abogen.normalization_settings import (
 )
 from abogen.llm_client import list_models, LLMClientError
 from abogen.kokoro_text_normalization import normalize_for_pipeline
+from abogen.tts_plugin.utils import is_plugin_registered
 from abogen.integrations.audiobookshelf import AudiobookshelfClient, AudiobookshelfConfig
 from abogen.integrations.calibre_opds import (
     CalibreOPDSClient,
@@ -63,7 +64,7 @@ def api_save_voice_profile() -> ResponseReturnValue:
     if profile is None:
         # Speaker Studio payload format
         provider = str(payload.get("provider") or "kokoro").strip().lower()
-        if provider not in {"kokoro", "supertonic"}:
+        if not is_plugin_registered(provider):
             provider = "kokoro"
         if provider == "supertonic":
             profile = {
@@ -230,7 +231,7 @@ def api_speaker_preview() -> ResponseReturnValue:
     use_gpu = settings.get("use_gpu", False)
 
     base_spec, speaker_name = split_profile_spec(voice)
-    resolved_provider = tts_provider if tts_provider in {"kokoro", "supertonic"} else ""
+    resolved_provider = tts_provider if is_plugin_registered(tts_provider) else ""
 
     if speaker_name:
         entry = normalize_profile_entry(load_profiles().get(speaker_name))
@@ -280,83 +281,7 @@ def api_speaker_preview() -> ResponseReturnValue:
 # --- Integration Routes ---
 
 
-def _opds_metadata_overrides(metadata_payload: Mapping[str, Any]) -> Dict[str, Any]:
+from abogen.domain.metadata_overrides import normalize_opds_metadata as _opds_metadata_overrides
-    metadata_overrides: Dict[str, Any] = {}
-
-    def _stringify_metadata_value(value: Any) -> str:
-        if value is None:
-            return ""
-        if isinstance(value, (list, tuple, set)):
-            parts = [str(item).strip() for item in value if item is not None]
-            parts = [part for part in parts if part]
-            return ", ".join(parts)
-        return str(value).strip()
-
-    raw_series = metadata_payload.get("series") or metadata_payload.get("series_name")
-    series_name = str(raw_series or "").strip()
-    if series_name:
-        metadata_overrides["series"] = series_name
-        metadata_overrides.setdefault("series_name", series_name)
-
-    series_index_value = (
-        metadata_payload.get("series_index")
-        or metadata_payload.get("series_position")
-        or metadata_payload.get("series_sequence")
-        or metadata_payload.get("book_number")
-    )
-    if series_index_value is not None:
-        series_index_text = str(series_index_value).strip()
-        if series_index_text:
-            metadata_overrides.setdefault("series_index", series_index_text)
-            metadata_overrides.setdefault("series_position", series_index_text)
-            metadata_overrides.setdefault("series_sequence", series_index_text)
-            metadata_overrides.setdefault("book_number", series_index_text)
-
-    tags_value = metadata_payload.get("tags") or metadata_payload.get("keywords")
-    if tags_value:
-        tags_text = _stringify_metadata_value(tags_value)
-        if tags_text:
-            metadata_overrides.setdefault("tags", tags_text)
-            metadata_overrides.setdefault("keywords", tags_text)
-            metadata_overrides.setdefault("genre", tags_text)
-
-    description_value = metadata_payload.get("description") or metadata_payload.get("summary")
-    if description_value:
-        description_text = _stringify_metadata_value(description_value)
-        if description_text:
-            metadata_overrides.setdefault("description", description_text)
-            metadata_overrides.setdefault("summary", description_text)
-
-    subtitle_value = (
-        metadata_payload.get("subtitle")
-        or metadata_payload.get("sub_title")
-        or metadata_payload.get("calibre_subtitle")
-    )
-    if subtitle_value:
-        subtitle_text = _stringify_metadata_value(subtitle_value)
-        if subtitle_text:
-            metadata_overrides.setdefault("subtitle", subtitle_text)
-
-    publisher_value = metadata_payload.get("publisher")
-    if publisher_value:
-        publisher_text = _stringify_metadata_value(publisher_value)
-        if publisher_text:
-            metadata_overrides.setdefault("publisher", publisher_text)
-
-    # Author mapping: Abogen templates look for either 'authors' or 'author'.
-    authors_value = (
-        metadata_payload.get("authors")
-        or metadata_payload.get("author")
-        or metadata_payload.get("creator")
-        or metadata_payload.get("dc_creator")
-    )
-    if authors_value:
-        authors_text = _stringify_metadata_value(authors_value)
-        if authors_text:
-            metadata_overrides.setdefault("authors", authors_text)
-            metadata_overrides.setdefault("author", authors_text)
-
-    return metadata_overrides
 
 @api_bp.get("/integrations/calibre-opds/feed")
 def api_calibre_opds_feed() -> ResponseReturnValue:

abogen/webui/routes/jobs.py

@@ -8,8 +8,8 @@ from flask.typing import ResponseReturnValue
 
 from abogen.webui.service import (
     JobStatus,
-    load_audiobookshelf_chapters,
     build_audiobookshelf_metadata,
+    load_audiobookshelf_chapters,
 )
 from abogen.webui.routes.utils.service import get_service
 from abogen.webui.routes.utils.form import render_jobs_panel
@@ -22,15 +22,22 @@ from abogen.webui.routes.utils.epub import (
 from abogen.webui.routes.utils.settings import (
     stored_integration_config,
     build_audiobookshelf_config,
-    coerce_bool,
 )
 from abogen.webui.routes.utils.common import existing_paths
-from abogen.integrations.audiobookshelf import AudiobookshelfClient, AudiobookshelfUploadError
+from abogen.infrastructure.exporters import ExportService
 
 logger = logging.getLogger(__name__)
 
 jobs_bp = Blueprint("jobs", __name__)
 
+
+def _resolve_cover(job: Any, config: Any) -> Optional[Path]:
+    """Resolve cover image path if enabled."""
+    if not config.send_cover or not job.cover_image_path:
+        return None
+    cover = job.cover_image_path if isinstance(job.cover_image_path, Path) else Path(str(job.cover_image_path))
+    return cover if cover.exists() else None
+
 @jobs_bp.get("/<job_id>")
 def job_detail(job_id: str) -> ResponseReturnValue:
     job = get_service().get_job(job_id)
@@ -98,24 +105,18 @@ def send_job_to_audiobookshelf(job_id: str) -> ResponseReturnValue:
         return _panel_response()
 
     settings = stored_integration_config("audiobookshelf")
-    if not settings or not coerce_bool(settings.get("enabled"), False):
+    if not settings or not settings.get("enabled"):
         job.add_log("Audiobookshelf upload skipped: integration is disabled.", level="warning")
         service._persist_state()
         return _panel_response()
 
     config = build_audiobookshelf_config(settings)
     if config is None:
-        job.add_log(
+        job.add_log("Audiobookshelf upload skipped: configure base URL, API token, and library ID first.", level="warning")
-            "Audiobookshelf upload skipped: configure base URL, API token, and library ID first.",
-            level="warning",
-        )
         service._persist_state()
         return _panel_response()
     if not config.folder_id:
-        job.add_log(
+        job.add_log("Audiobookshelf upload skipped: enter the folder name or ID in the Audiobookshelf settings.", level="warning")
-            "Audiobookshelf upload skipped: enter the folder name or ID in the Audiobookshelf settings.",
-            level="warning",
-        )
         service._persist_state()
         return _panel_response()
 
@@ -125,39 +126,20 @@ def send_job_to_audiobookshelf(job_id: str) -> ResponseReturnValue:
         service._persist_state()
         return _panel_response()
 
-    cover_path = None
-    if config.send_cover and job.cover_image_path:
-        cover_candidate = job.cover_image_path
-        if not isinstance(cover_candidate, Path):
-            cover_candidate = Path(str(cover_candidate))
-        if cover_candidate.exists():
-            cover_path = cover_candidate
-
-    subtitles = existing_paths(job.result.subtitle_paths) if config.send_subtitles else None
-    chapters = load_audiobookshelf_chapters(job) if config.send_chapters else None
-    metadata = build_audiobookshelf_metadata(job)
-    display_title = metadata.get("title") or audio_path.stem
     overwrite_requested = request.form.get("overwrite") == "true" or request.args.get("overwrite") == "true"
 
+    if not overwrite_requested:
+        from abogen.integrations.audiobookshelf import AudiobookshelfClient, AudiobookshelfUploadError
+        metadata = build_audiobookshelf_metadata(job)
+        display_title = metadata.get("title") or audio_path.stem
         try:
-        client = AudiobookshelfClient(config)
+            existing_items = AudiobookshelfClient(config).find_existing_items(display_title, folder_id=config.folder_id)
-    except ValueError as exc:
-        job.add_log(f"Audiobookshelf configuration error: {exc}", level="error")
-        service._persist_state()
-        return _panel_response()
-
-    try:
-        existing_items = client.find_existing_items(display_title, folder_id=config.folder_id)
         except AudiobookshelfUploadError as exc:
             job.add_log(f"Audiobookshelf lookup failed: {exc}", level="error")
             service._persist_state()
             return _panel_response()
-
+        if existing_items:
-    if existing_items and not overwrite_requested:
+            job.add_log(f"Audiobookshelf already contains '{display_title}'. Awaiting overwrite confirmation.", level="warning")
-        job.add_log(
-            f"Audiobookshelf already contains '{display_title}'. Awaiting overwrite confirmation.",
-            level="warning",
-        )
             service._persist_state()
             if request.headers.get("HX-Request"):
                 detail = {
@@ -171,37 +153,22 @@ def send_job_to_audiobookshelf(job_id: str) -> ResponseReturnValue:
                 return Response("", status=204, headers=headers)
             return _panel_response()
 
-    if existing_items and overwrite_requested:
-        try:
-            client.delete_items(existing_items)
-        except AudiobookshelfUploadError as exc:
-            job.add_log(f"Audiobookshelf overwrite aborted: {exc}", level="error")
-            service._persist_state()
-            return _panel_response()
-        else:
-            job.add_log(
-                f"Removed {len(existing_items)} existing Audiobookshelf item(s) prior to overwrite.",
-                level="info",
-            )
-
     job.add_log("Audiobookshelf upload triggered manually.", level="info")
+    export_svc = ExportService()
     try:
-        client.upload_audiobook(
+        export_svc.upload_audiobookshelf(
+            job,
             audio_path,
-            metadata=metadata,
+            existing_paths(job.result.subtitle_paths),
-            cover_path=cover_path,
+            load_audiobookshelf_chapters(job) if config.send_chapters else None,
-            chapters=chapters,
+            build_audiobookshelf_metadata(job),
-            subtitles=subtitles,
+            cover_path=_resolve_cover(job, config),
+            config=config,
+            log_callback=lambda msg, lvl="info": job.add_log(msg, level=lvl),
         )
-    except AudiobookshelfUploadError as exc:
-        job.add_log(f"Audiobookshelf upload failed: {exc}", level="error")
     except Exception as exc:
         job.add_log(f"Audiobookshelf integration error: {exc}", level="error")
-    else:
-        job.add_log("Audiobookshelf upload queued.", level="success")
-    finally:
     service._persist_state()
-
     return _panel_response()
 
 @jobs_bp.post("/clear-finished")

abogen/webui/routes/settings.py

@@ -8,21 +8,15 @@ from flask.typing import ResponseReturnValue
 
 from abogen.webui.routes.utils.settings import (
     load_settings,
-    load_integration_settings,
     save_settings,
-    stored_integration_config,
-    coerce_bool,
-    coerce_int,
     SAVE_MODE_LABELS,
     llm_ready,
-    _NORMALIZATION_BOOLEAN_KEYS,
-    _NORMALIZATION_STRING_KEYS,
-    _DEFAULT_ANALYSIS_THRESHOLD,
 )
 from abogen.webui.routes.utils.voice import template_options
+from abogen.webui.services.settings_service import apply_form_to_settings
 from abogen.webui.debug_tts_runner import run_debug_tts_wavs
 from abogen.debug_tts_samples import DEBUG_TTS_SAMPLES
-from abogen.utils import get_user_output_path, load_config
+from abogen.utils import get_user_output_path
 
 settings_bp = Blueprint("settings", __name__)
 
@@ -37,151 +31,7 @@ _NORMALIZATION_SAMPLES = {
 @settings_bp.post("/update")
 def update_settings() -> ResponseReturnValue:
     current = load_settings()
-    form = request.form
+    apply_form_to_settings(current, request.form)
-
-    # General settings
-    current["language"] = (form.get("language") or "en").strip()
-    current["default_speaker"] = (form.get("default_speaker") or "").strip()
-    current["default_voice"] = (form.get("default_voice") or "").strip()
-    try:
-        current["supertonic_total_steps"] = max(2, min(15, int(form.get("supertonic_total_steps", current.get("supertonic_total_steps", 5)))))
-    except (TypeError, ValueError):
-        pass
-    try:
-        current["supertonic_speed"] = max(0.7, min(2.0, float(form.get("supertonic_speed", current.get("supertonic_speed", 1.0)))))
-    except (TypeError, ValueError):
-        pass
-    current["output_format"] = (form.get("output_format") or "mp3").strip()
-    current["subtitle_mode"] = (form.get("subtitle_mode") or "Disabled").strip()
-    current["subtitle_format"] = (form.get("subtitle_format") or "srt").strip()
-    current["save_mode"] = (form.get("save_mode") or "save_next_to_input").strip()
-    
-    current["replace_single_newlines"] = coerce_bool(form.get("replace_single_newlines"), False)
-    current["use_gpu"] = coerce_bool(form.get("use_gpu"), False)
-    current["save_chapters_separately"] = coerce_bool(form.get("save_chapters_separately"), False)
-    current["merge_chapters_at_end"] = coerce_bool(form.get("merge_chapters_at_end"), True)
-    current["save_as_project"] = coerce_bool(form.get("save_as_project"), False)
-    current["separate_chapters_format"] = (form.get("separate_chapters_format") or "wav").strip()
-    
-    try:
-        current["silence_between_chapters"] = max(0.0, float(form.get("silence_between_chapters", 2.0)))
-    except ValueError:
-        pass
-        
-    try:
-        current["chapter_intro_delay"] = max(0.0, float(form.get("chapter_intro_delay", 0.5)))
-    except ValueError:
-        pass
-        
-    current["read_title_intro"] = coerce_bool(form.get("read_title_intro"), False)
-    current["read_closing_outro"] = coerce_bool(form.get("read_closing_outro"), True)
-    current["normalize_chapter_opening_caps"] = coerce_bool(form.get("normalize_chapter_opening_caps"), True)
-    current["auto_prefix_chapter_titles"] = coerce_bool(form.get("auto_prefix_chapter_titles"), True)
-    
-    try:
-        current["max_subtitle_words"] = max(1, int(form.get("max_subtitle_words", 50)))
-    except ValueError:
-        pass
-        
-    current["chunk_level"] = (form.get("chunk_level") or "paragraph").strip()
-    current["generate_epub3"] = coerce_bool(form.get("generate_epub3"), False)
-    
-    current["speaker_analysis_threshold"] = coerce_int(
-        form.get("speaker_analysis_threshold"),
-        _DEFAULT_ANALYSIS_THRESHOLD,
-        minimum=1,
-        maximum=25,
-    )
-
-    def _extract_checkbox(name: str, default: bool) -> bool:
-        values = form.getlist(name) if hasattr(form, "getlist") else []
-        if values:
-            return coerce_bool(values[-1], default)
-        if hasattr(form, "__contains__") and name in form:
-            return False
-        return default
-
-    # Normalization settings
-    for key in _NORMALIZATION_BOOLEAN_KEYS:
-        current[key] = _extract_checkbox(key, bool(current.get(key, True)))
-    for key in _NORMALIZATION_STRING_KEYS:
-        if hasattr(form, "__contains__") and key in form:
-            current[key] = (form.get(key) or "").strip()
-
-    # Integrations
-    # `load_settings()` returns only the general settings subset and intentionally
-    # does not include stored integrations. Seed them from the stored config so
-    # saving unrelated settings cannot wipe credentials/tokens.
-    current_integrations: dict[str, dict[str, Any]] = {}
-    cfg = load_config() or {}
-    stored_integrations = cfg.get("integrations")
-    if isinstance(stored_integrations, Mapping):
-        for name, payload in stored_integrations.items():
-            if isinstance(name, str) and isinstance(payload, Mapping):
-                current_integrations[name] = dict(payload)
-    # Ensure known integrations are loaded even if the config is still in legacy format.
-    for name in ("audiobookshelf", "calibre_opds"):
-        stored = stored_integration_config(name)
-        if stored and name not in current_integrations:
-            current_integrations[name] = dict(stored)
-    current["integrations"] = current_integrations
-
-    # Audiobookshelf
-    abs_enabled = coerce_bool(form.get("audiobookshelf_enabled"), False)
-    abs_url = (form.get("audiobookshelf_base_url") or "").strip()
-    abs_token = (form.get("audiobookshelf_api_token") or "").strip()
-    abs_library = (form.get("audiobookshelf_library_id") or "").strip()
-    abs_folder = (form.get("audiobookshelf_folder_id") or "").strip()
-    abs_verify = coerce_bool(form.get("audiobookshelf_verify_ssl"), True)
-    abs_auto_send = coerce_bool(form.get("audiobookshelf_auto_send"), False)
-    abs_cover = coerce_bool(form.get("audiobookshelf_send_cover"), True)
-    abs_chapters = coerce_bool(form.get("audiobookshelf_send_chapters"), True)
-    abs_subtitles = coerce_bool(form.get("audiobookshelf_send_subtitles"), False)
-    
-    try:
-        abs_timeout = max(1.0, float(form.get("audiobookshelf_timeout", 30.0)))
-    except ValueError:
-        abs_timeout = 30.0
-
-    # Preserve existing token if not provided and not cleared
-    if not abs_token and not coerce_bool(form.get("audiobookshelf_api_token_clear"), False):
-        existing_abs = current["integrations"].get("audiobookshelf", {})
-        abs_token = existing_abs.get("api_token", "")
-
-    current["integrations"]["audiobookshelf"] = {
-        "enabled": abs_enabled,
-        "base_url": abs_url,
-        "api_token": abs_token,
-        "library_id": abs_library,
-        "folder_id": abs_folder,
-        "verify_ssl": abs_verify,
-        "auto_send": abs_auto_send,
-        "send_cover": abs_cover,
-        "send_chapters": abs_chapters,
-        "send_subtitles": abs_subtitles,
-        "timeout": abs_timeout,
-    }
-    
-    # Calibre OPDS
-    calibre_enabled = coerce_bool(form.get("calibre_opds_enabled"), False)
-    calibre_url = (form.get("calibre_opds_base_url") or "").strip()
-    calibre_user = (form.get("calibre_opds_username") or "").strip()
-    calibre_pass = (form.get("calibre_opds_password") or "").strip()
-    calibre_verify = coerce_bool(form.get("calibre_opds_verify_ssl"), True)
-    
-    # Preserve existing password if not provided and not cleared
-    if not calibre_pass and not coerce_bool(form.get("calibre_opds_password_clear"), False):
-        existing_calibre = current["integrations"].get("calibre_opds", {})
-        calibre_pass = existing_calibre.get("password", "")
-    
-    current["integrations"]["calibre_opds"] = {
-        "enabled": calibre_enabled,
-        "base_url": calibre_url,
-        "username": calibre_user,
-        "password": calibre_pass,
-        "verify_ssl": calibre_verify,
-    }
-
     save_settings(current)
     flash("Settings updated successfully.", "success")
     return redirect(url_for("settings.settings_page"))

abogen/webui/routes/utils/common.py

@@ -1,24 +1,38 @@
-from typing import Any, Optional, Tuple, Iterable, List
+from typing import Any, Optional, Tuple, Iterable, List, Mapping
 from pathlib import Path
 
-def split_profile_spec(value: Any) -> Tuple[str, Optional[str]]:
+from abogen.domain.settings_core import coerce_bool, split_profile_spec  # noqa: F401
-    text = str(value or "").strip()
-    if not text:
-        return "", None
-    lowered = text.lower()
-    if lowered.startswith("profile:") or lowered.startswith("speaker:"):
-        _, _, remainder = text.partition(":")
-        name = remainder.strip()
-        return "", name or None
-    return text, None
 
 
 def split_speaker_spec(value: Any) -> Tuple[str, Optional[str]]:
     """Preferred alias for split_profile_spec (supports 'speaker:' and legacy 'profile:')."""
-
     return split_profile_spec(value)
 
+
 def existing_paths(paths: Optional[Iterable[Path]]) -> List[Path]:
     if not paths:
         return []
     return [p for p in paths if p.exists()]
+
+
+def extract_checkbox(form: Mapping[str, Any], name: str, default: bool) -> bool:
+    """Extract a boolean checkbox value from a form-like mapping.
+
+    Handles both multi-value forms (Flask's `getlist`) and simple mappings.
+    If the checkbox name is present but has no value, it means unchecked (False).
+    """
+    values: List[str] = []
+    getter = getattr(form, "getlist", None)
+    if callable(getter):
+        raw_values = getter(name)
+        if raw_values:
+            values = list(raw_values)
+    else:
+        raw_flag = form.get(name)
+        if raw_flag is not None:
+            values = [raw_flag]
+    if values:
+        return coerce_bool(values[-1], default)
+    if name in form:
+        return False
+    return default

abogen/webui/routes/utils/form.py

@@ -1,12 +1,17 @@
-import re
 import time
 import uuid
 from typing import Any, Dict, Iterable, List, Mapping, Optional, Tuple, cast
 from flask import request, render_template, jsonify
 from flask.typing import ResponseReturnValue
 
+from abogen.domain.chapter_classification import (
+    supplement_score,
+    should_preselect_chapter,
+    ensure_at_least_one_chapter_enabled,
+)
 from abogen.webui.service import PendingJob, JobStatus
 from abogen.webui.routes.utils.service import get_service
+from abogen.tts_plugin.utils import is_plugin_registered
 from abogen.webui.routes.utils.settings import (
     load_settings,
     coerce_bool,
@@ -28,11 +33,11 @@ from abogen.webui.routes.utils.voice import (
 )
 from abogen.webui.routes.utils.entity import sync_pronunciation_overrides
 from abogen.webui.routes.utils.epub import job_download_flags
-from abogen.webui.routes.utils.common import split_profile_spec
+from abogen.webui.routes.utils.common import split_profile_spec, extract_checkbox
 from abogen.utils import calculate_text_length
 from abogen.voice_profiles import serialize_profiles, normalize_profile_entry
 from abogen.chunking import ChunkLevel, build_chunks_for_chapters
-from abogen.constants import VOICES_INTERNAL
+from abogen.tts_plugin.utils import get_default_voice
 from abogen.speaker_configs import get_config
 from abogen.kokoro_text_normalization import normalize_roman_numeral_titles
 from dataclasses import dataclass
@@ -65,109 +70,6 @@ _WIZARD_STEP_META = {
     },
 }
 
-_SUPPLEMENT_TITLE_PATTERNS: List[tuple[re.Pattern[str], float]] = [
-    (re.compile(r"\btitle\s+page\b"), 3.0),
-    (re.compile(r"\bcopyright\b"), 2.4),
-    (re.compile(r"\btable\s+of\s+contents\b"), 2.8),
-    (re.compile(r"\bcontents\b"), 2.0),
-    (re.compile(r"\backnowledg(e)?ments?\b"), 2.0),
-    (re.compile(r"\bdedication\b"), 2.0),
-    (re.compile(r"\babout\s+the\s+author(s)?\b"), 2.4),
-    (re.compile(r"\balso\s+by\b"), 2.0),
-    (re.compile(r"\bpraise\s+for\b"), 2.0),
-    (re.compile(r"\bcolophon\b"), 2.2),
-    (re.compile(r"\bpublication\s+data\b"), 2.2),
-    (re.compile(r"\btranscriber'?s?\s+note\b"), 2.2),
-    (re.compile(r"\bglossary\b"), 2.0),
-    (re.compile(r"\bindex\b"), 2.0),
-    (re.compile(r"\bbibliograph(y|ies)\b"), 2.0),
-    (re.compile(r"\breferences\b"), 1.8),
-    (re.compile(r"\bappendix\b"), 1.9),
-]
-
-_CONTENT_TITLE_PATTERNS: List[re.Pattern[str]] = [
-    re.compile(r"\bchapter\b"),
-    re.compile(r"\bbook\b"),
-    re.compile(r"\bpart\b"),
-    re.compile(r"\bsection\b"),
-    re.compile(r"\bscene\b"),
-    re.compile(r"\bprologue\b"),
-    re.compile(r"\bepilogue\b"),
-    re.compile(r"\bintroduction\b"),
-    re.compile(r"\bstory\b"),
-]
-
-_SUPPLEMENT_TEXT_KEYWORDS: List[tuple[str, float]] = [
-    ("copyright", 1.2),
-    ("all rights reserved", 1.1),
-    ("isbn", 0.9),
-    ("library of congress", 1.0),
-    ("table of contents", 1.0),
-    ("dedicated to", 0.8),
-    ("acknowledg", 0.8),
-    ("printed in", 0.6),
-    ("permission", 0.6),
-    ("publisher", 0.5),
-    ("praise for", 0.9),
-    ("also by", 0.9),
-    ("glossary", 0.8),
-    ("index", 0.8),
-    ("newsletter", 3.2),
-    ("mailing list", 2.6),
-    ("sign-up", 2.2),
-]
-
-def supplement_score(title: str, text: str, index: int) -> float:
-    normalized_title = (title or "").lower()
-    score = 0.0
-
-    for pattern, weight in _SUPPLEMENT_TITLE_PATTERNS:
-        if pattern.search(normalized_title):
-            score += weight
-
-    for pattern in _CONTENT_TITLE_PATTERNS:
-        if pattern.search(normalized_title):
-            score -= 2.0
-
-    stripped_text = (text or "").strip()
-    length = len(stripped_text)
-    if length <= 150:
-        score += 0.9
-    elif length <= 400:
-        score += 0.6
-    elif length <= 800:
-        score += 0.35
-
-    lowercase_text = stripped_text.lower()
-    for keyword, weight in _SUPPLEMENT_TEXT_KEYWORDS:
-        if keyword in lowercase_text:
-            score += weight
-
-    if index == 0 and score > 0:
-        score += 0.25
-
-    return score
-
-
-def should_preselect_chapter(
-    title: str,
-    text: str,
-    index: int,
-    total_count: int,
-) -> bool:
-    if total_count <= 1:
-        return True
-    score = supplement_score(title, text, index)
-    return score < 1.9
-
-
-def ensure_at_least_one_chapter_enabled(chapters: List[Dict[str, Any]]) -> None:
-    if not chapters:
-        return
-    if any(chapter.get("enabled") for chapter in chapters):
-        return
-    best_index = max(range(len(chapters)), key=lambda idx: chapters[idx].get("characters", 0))
-    chapters[best_index]["enabled"] = True
 
 def apply_prepare_form(
     pending: PendingJob, form: Mapping[str, Any]
@@ -536,28 +438,11 @@ def apply_book_step_form(
     else:
         pending.normalize_chapter_opening_caps = caps_default
 
-    def _extract_checkbox(name: str, default: bool) -> bool:
-        values: List[str] = []
-        getter = getattr(form, "getlist", None)
-        if callable(getter):
-            raw_values = getter(name)
-            if raw_values:
-                values = list(cast(Iterable[str], raw_values))
-        else:
-            raw_flag = form.get(name)
-            if raw_flag is not None:
-                values = [raw_flag]
-        if values:
-            return coerce_bool(values[-1], default)
-        if hasattr(form, "__contains__") and name in form:
-            return False
-        return default
-
     overrides_existing = getattr(pending, "normalization_overrides", None)
     overrides: Dict[str, Any] = dict(overrides_existing or {})
     for key in _NORMALIZATION_BOOLEAN_KEYS:
         default_toggle = overrides.get(key, bool(settings.get(key, True)))
-        overrides[key] = _extract_checkbox(key, default_toggle)
+        overrides[key] = extract_checkbox(form, key, default_toggle)
     for key in _NORMALIZATION_STRING_KEYS:
         default_val = overrides.get(key, str(settings.get(key, "")))
         val = form.get(key)
@@ -579,7 +464,7 @@ def apply_book_step_form(
     # spec (e.g. "speaker:Name" for saved speakers, or a Kokoro mix formula).
     # This enables mixed-provider conversions (e.g. narrator=SuperTonic, characters=Kokoro).
     provider_value = str(form.get("tts_provider") or "").strip().lower()
-    if provider_value in {"kokoro", "supertonic"}:
+    if is_plugin_registered(provider_value):
         pending.tts_provider = provider_value
 
     # Determine the base speaker selection (saved speaker ref or raw voice).
@@ -616,8 +501,8 @@ def apply_book_step_form(
         custom_formula = ""
 
     base_voice_spec = resolved_default_voice or narrator_voice_raw
-    if not base_voice_spec and VOICES_INTERNAL:
+    if not base_voice_spec:
-        base_voice_spec = VOICES_INTERNAL[0]
+        base_voice_spec = get_default_voice("kokoro")
 
     voice_choice, resolved_language, selected_profile = resolve_voice_choice(
         pending.language,
@@ -796,8 +681,8 @@ def build_pending_job_from_extraction(
         profile_selection = inferred_profile
 
     base_voice = base_voice_input or resolved_default_voice or str(default_voice_setting).strip()
-    if not base_voice and VOICES_INTERNAL:
+    if not base_voice:
-        base_voice = VOICES_INTERNAL[0]
+        base_voice = get_default_voice("kokoro")
     selected_speaker_config = (form.get("speaker_config") or "").strip()
     speaker_config_payload = get_config(selected_speaker_config) if selected_speaker_config else None
 
@@ -885,25 +770,10 @@ def build_pending_job_from_extraction(
         apply_config=bool(speaker_config_payload),
     )
 
-    def _extract_checkbox(name: str, default: bool) -> bool:
-        values: List[str] = []
-        getter = getattr(form, "getlist", None)
-        if callable(getter):
-            raw_values = getter(name)
-            if raw_values:
-                values = list(cast(Iterable[str], raw_values))
-        else:
-            raw_flag = form.get(name)
-            if raw_flag is not None:
-                values = [raw_flag]
-        if values:
-            return coerce_bool(values[-1], default)
-        return default
-
     normalization_overrides = {}
     for key in _NORMALIZATION_BOOLEAN_KEYS:
         default_val = bool(settings.get(key, True))
-        normalization_overrides[key] = _extract_checkbox(key, default_val)
+        normalization_overrides[key] = extract_checkbox(form, key, default_val)
 
     for key in _NORMALIZATION_STRING_KEYS:
         default_val = str(settings.get(key, ""))

abogen/webui/routes/utils/settings.py

@@ -1,108 +1,24 @@
 import os
-import re
 from typing import Any, Dict, Mapping, Optional
 
-from abogen.constants import (
-    LANGUAGE_DESCRIPTIONS,
-    SUBTITLE_FORMATS,
-    SUPPORTED_SOUND_FORMATS,
-    VOICES_INTERNAL,
-)
-from abogen.normalization_settings import (
-    DEFAULT_LLM_PROMPT,
-    environment_llm_defaults,
-)
-from abogen.utils import load_config, save_config
 from abogen.integrations.calibre_opds import CalibreOPDSClient
 from abogen.integrations.audiobookshelf import AudiobookshelfConfig
-from abogen.webui.routes.utils.common import split_profile_spec
+from abogen.utils import load_config, save_config
-
+from abogen.domain.settings_core import (
-SAVE_MODE_LABELS = {
+    CHUNK_LEVEL_OPTIONS,
-    "save_next_to_input": "Save next to input file",
+    CHUNK_LEVEL_VALUES,
-    "save_to_desktop": "Save to Desktop",
+    DEFAULT_ANALYSIS_THRESHOLD,
-    "choose_output_folder": "Choose output folder",
+    SAVE_MODE_LABELS,
-    "default_output": "Use default save location",
+    _NORMALIZATION_BOOLEAN_KEYS,
-}
+    _NORMALIZATION_STRING_KEYS,
-
+    coerce_bool,
-LEGACY_SAVE_MODE_MAP = {label: key for key, label in SAVE_MODE_LABELS.items()}
+    coerce_float,
-
+    coerce_int,
-_CHUNK_LEVEL_OPTIONS = [
+    integration_defaults,
-    {"value": "paragraph", "label": "Paragraphs"},
+    load_settings,
-    {"value": "sentence", "label": "Sentences"},
+    llm_ready,
-]
+    settings_defaults,
-
+)
-_CHUNK_LEVEL_VALUES = {option["value"] for option in _CHUNK_LEVEL_OPTIONS}
-
-_DEFAULT_ANALYSIS_THRESHOLD = 3
-
-_APOSTROPHE_MODE_OPTIONS = [
-    {"value": "off", "label": "Off"},
-    {"value": "spacy", "label": "spaCy (built-in)"},
-    {"value": "llm", "label": "LLM assisted"},
-]
-
-_NORMALIZATION_BOOLEAN_KEYS = {
-    "normalization_numbers",
-    "normalization_titles",
-    "normalization_terminal",
-    "normalization_phoneme_hints",
-    "normalization_caps_quotes",
-    "normalization_currency",
-    "normalization_footnotes",
-    "normalization_internet_slang",
-    "normalization_apostrophes_contractions",
-    "normalization_apostrophes_plural_possessives",
-    "normalization_apostrophes_sibilant_possessives",
-    "normalization_apostrophes_decades",
-    "normalization_apostrophes_leading_elisions",
-    "normalization_contraction_aux_be",
-    "normalization_contraction_aux_have",
-    "normalization_contraction_modal_will",
-    "normalization_contraction_modal_would",
-    "normalization_contraction_negation_not",
-    "normalization_contraction_let_us",
-}
-
-_NORMALIZATION_STRING_KEYS = {
-    "normalization_numbers_year_style",
-    "normalization_apostrophe_mode",
-}
-
-BOOLEAN_SETTINGS = {
-    "replace_single_newlines",
-    "use_gpu",
-    "save_chapters_separately",
-    "merge_chapters_at_end",
-    "save_as_project",
-    "generate_epub3",
-    "enable_entity_recognition",
-    "read_title_intro",
-    "read_closing_outro",
-    "auto_prefix_chapter_titles",
-    "normalize_chapter_opening_caps",
-    "normalization_numbers",
-    "normalization_titles",
-    "normalization_terminal",
-    "normalization_phoneme_hints",
-    "normalization_caps_quotes",
-    "normalization_currency",
-    "normalization_footnotes",
-    "normalization_internet_slang",
-    "normalization_apostrophes_contractions",
-    "normalization_apostrophes_plural_possessives",
-    "normalization_apostrophes_sibilant_possessives",
-    "normalization_apostrophes_decades",
-    "normalization_apostrophes_leading_elisions",
-    "normalization_contraction_aux_be",
-    "normalization_contraction_aux_have",
-    "normalization_contraction_modal_will",
-    "normalization_contraction_modal_would",
-    "normalization_contraction_negation_not",
-    "normalization_contraction_let_us",
-}
-
-FLOAT_SETTINGS = {"silence_between_chapters", "chapter_intro_delay", "llm_timeout"}
-INT_SETTINGS = {"max_subtitle_words", "speaker_analysis_threshold"}
 
 _NORMALIZATION_GROUPS = [
     {
@@ -136,246 +52,16 @@ _NORMALIZATION_GROUPS = [
     }
 ]
 
+_APOSTROPHE_MODE_OPTIONS = [
+    {"value": "off", "label": "Off"},
+    {"value": "spacy", "label": "spaCy (built-in)"},
+    {"value": "llm", "label": "LLM assisted"},
+]
 
-def integration_defaults() -> Dict[str, Dict[str, Any]]:
+# Backward-compatible aliases for modules still referencing old underscore-prefixed names
-    return {
+_DEFAULT_ANALYSIS_THRESHOLD = DEFAULT_ANALYSIS_THRESHOLD
-        "calibre_opds": {
+_CHUNK_LEVEL_OPTIONS = CHUNK_LEVEL_OPTIONS
-            "enabled": False,
+_CHUNK_LEVEL_VALUES = CHUNK_LEVEL_VALUES
-            "base_url": "",
-            "username": "",
-            "password": "",
-            "verify_ssl": True,
-        },
-        "audiobookshelf": {
-            "enabled": False,
-            "base_url": "",
-            "api_token": "",
-            "library_id": "",
-            "collection_id": "",
-            "folder_id": "",
-            "verify_ssl": True,
-            "send_cover": True,
-            "send_chapters": True,
-            "send_subtitles": False,
-            "auto_send": False,
-            "timeout": 30.0,
-        },
-    }
-
-
-def has_output_override() -> bool:
-    return bool(os.environ.get("ABOGEN_OUTPUT_DIR") or os.environ.get("ABOGEN_OUTPUT_ROOT"))
-
-
-def settings_defaults() -> Dict[str, Any]:
-    llm_env_defaults = environment_llm_defaults()
-    return {
-        "output_format": "wav",
-        "subtitle_format": "srt",
-        "save_mode": "default_output" if has_output_override() else "save_next_to_input",
-        "default_speaker": "",
-        "default_voice": VOICES_INTERNAL[0] if VOICES_INTERNAL else "",
-        "supertonic_total_steps": 5,
-        "supertonic_speed": 1.0,
-        "replace_single_newlines": False,
-        "use_gpu": True,
-        "save_chapters_separately": False,
-        "merge_chapters_at_end": True,
-        "save_as_project": False,
-        "separate_chapters_format": "wav",
-        "silence_between_chapters": 2.0,
-        "chapter_intro_delay": 0.5,
-        "read_title_intro": False,
-        "read_closing_outro": True,
-        "normalize_chapter_opening_caps": True,
-        "max_subtitle_words": 50,
-        "chunk_level": "paragraph",
-        "enable_entity_recognition": True,
-        "generate_epub3": False,
-        "auto_prefix_chapter_titles": True,
-        "speaker_analysis_threshold": _DEFAULT_ANALYSIS_THRESHOLD,
-        "speaker_pronunciation_sentence": "This is {{name}} speaking.",
-        "speaker_random_languages": [],
-        "llm_base_url": llm_env_defaults.get("llm_base_url", ""),
-        "llm_api_key": llm_env_defaults.get("llm_api_key", ""),
-        "llm_model": llm_env_defaults.get("llm_model", ""),
-        "llm_timeout": llm_env_defaults.get("llm_timeout", 30.0),
-        "llm_prompt": llm_env_defaults.get("llm_prompt", DEFAULT_LLM_PROMPT),
-        "llm_context_mode": llm_env_defaults.get("llm_context_mode", "sentence"),
-        "normalization_numbers": True,
-        "normalization_currency": True,
-        "normalization_footnotes": True,
-        "normalization_titles": True,
-        "normalization_terminal": True,
-        "normalization_phoneme_hints": True,
-        "normalization_caps_quotes": True,
-        "normalization_internet_slang": False,
-        "normalization_apostrophes_contractions": True,
-        "normalization_apostrophes_plural_possessives": True,
-        "normalization_apostrophes_sibilant_possessives": True,
-        "normalization_apostrophes_decades": True,
-        "normalization_apostrophes_leading_elisions": True,
-        "normalization_apostrophe_mode": "spacy",
-        "normalization_numbers_year_style": "american",
-        "normalization_contraction_aux_be": True,
-        "normalization_contraction_aux_have": True,
-        "normalization_contraction_modal_will": True,
-        "normalization_contraction_modal_would": True,
-        "normalization_contraction_negation_not": True,
-        "normalization_contraction_let_us": True,
-    }
-
-
-def llm_ready(settings: Mapping[str, Any]) -> bool:
-    base_url = str(settings.get("llm_base_url") or "").strip()
-    return bool(base_url)
-
-
-_PROMPT_TOKEN_RE = re.compile(r"{{\s*([a-zA-Z0-9_]+)\s*}}")
-
-
-def render_prompt_template(template: str, context: Mapping[str, str]) -> str:
-    if not template:
-        return ""
-
-    def _replace(match: re.Match[str]) -> str:
-        key = match.group(1)
-        return context.get(key, "")
-
-    return _PROMPT_TOKEN_RE.sub(_replace, template)
-
-
-def coerce_bool(value: Any, default: bool) -> bool:
-    if isinstance(value, bool):
-        return value
-    if isinstance(value, str):
-        return value.lower() in {"true", "1", "yes", "on"}
-    if value is None:
-        return default
-    return bool(value)
-
-
-def coerce_float(value: Any, default: float) -> float:
-    try:
-        return max(0.0, float(value))
-    except (TypeError, ValueError):
-        return default
-
-
-def coerce_int(value: Any, default: int, *, minimum: int = 1, maximum: int = 200) -> int:
-    try:
-        parsed = int(value)
-    except (TypeError, ValueError):
-        return default
-    return max(minimum, min(parsed, maximum))
-
-
-def normalize_save_mode(value: Any, default: str) -> str:
-    if isinstance(value, str):
-        if value in SAVE_MODE_LABELS:
-            return value
-        if value in LEGACY_SAVE_MODE_MAP:
-            return LEGACY_SAVE_MODE_MAP[value]
-    return default
-
-
-def normalize_setting_value(key: str, value: Any, defaults: Dict[str, Any]) -> Any:
-    if key in BOOLEAN_SETTINGS:
-        return coerce_bool(value, defaults[key])
-    if key in FLOAT_SETTINGS:
-        return coerce_float(value, defaults[key])
-    if key in INT_SETTINGS:
-        return coerce_int(value, defaults[key])
-    if key == "save_mode":
-        return normalize_save_mode(value, defaults[key])
-    if key == "output_format":
-        return value if value in SUPPORTED_SOUND_FORMATS else defaults[key]
-    if key == "subtitle_format":
-        valid = {item[0] for item in SUBTITLE_FORMATS}
-        return value if value in valid else defaults[key]
-    if key == "separate_chapters_format":
-        if isinstance(value, str):
-            normalized = value.lower()
-            if normalized in {"wav", "flac", "mp3", "opus"}:
-                return normalized
-        return defaults[key]
-    if key == "default_voice":
-        if isinstance(value, str):
-            text = value.strip()
-            if not text:
-                return defaults[key]
-            spec, profile_name = split_profile_spec(text)
-            if profile_name:
-                return f"speaker:{profile_name}"
-            return spec
-        return defaults[key]
-    if key == "default_speaker":
-        if isinstance(value, str):
-            text = value.strip()
-            if not text:
-                return ""
-            spec, profile_name = split_profile_spec(text)
-            if profile_name:
-                return f"speaker:{profile_name}"
-            return spec
-        return ""
-    if key == "chunk_level":
-        if isinstance(value, str) and value in _CHUNK_LEVEL_VALUES:
-            return value
-        return defaults[key]
-    if key == "normalization_apostrophe_mode":
-        if isinstance(value, str):
-            normalized_mode = value.strip().lower()
-            if normalized_mode in {"off", "spacy", "llm"}:
-                return normalized_mode
-        return defaults[key]
-        if key == "normalization_numbers_year_style":
-            if isinstance(value, str):
-                normalized_style = value.strip().lower()
-                if normalized_style in {"american", "off"}:
-                    return normalized_style
-            return defaults[key]
-    if key == "llm_context_mode":
-        if isinstance(value, str):
-            normalized_scope = value.strip().lower()
-            if normalized_scope == "sentence":
-                return normalized_scope
-        return defaults[key]
-    if key == "llm_prompt":
-        candidate = str(value or "").strip()
-        return candidate if candidate else defaults[key]
-    if key in {"llm_base_url", "llm_api_key", "llm_model"}:
-        return str(value or "").strip()
-    if key == "speaker_random_languages":
-        if isinstance(value, (list, tuple, set)):
-            return [code for code in value if isinstance(code, str) and code in LANGUAGE_DESCRIPTIONS]
-        if isinstance(value, str):
-            parts = [item.strip().lower() for item in value.split(",") if item.strip()]
-            return [code for code in parts if code in LANGUAGE_DESCRIPTIONS]
-        return defaults.get(key, [])
-    if key == "supertonic_total_steps":
-        try:
-            steps = int(value)
-        except (TypeError, ValueError):
-            return defaults.get(key, 5)
-        return max(2, min(15, steps))
-    if key == "supertonic_speed":
-        try:
-            speed = float(value)
-        except (TypeError, ValueError):
-            return defaults.get(key, 1.0)
-        return max(0.7, min(2.0, speed))
-    return value if value is not None else defaults.get(key)
-
-
-def load_settings() -> Dict[str, Any]:
-    defaults = settings_defaults()
-    cfg = load_config() or {}
-    settings: Dict[str, Any] = {}
-    for key, default in defaults.items():
-        raw_value = cfg.get(key, default)
-        settings[key] = normalize_setting_value(key, raw_value, defaults)
-    return settings
 
 
 def load_integration_settings() -> Dict[str, Dict[str, Any]]:

abogen/webui/routes/utils/synthesize.py

@@ -6,38 +6,43 @@ import soundfile as sf
 from flask import current_app, send_file
 from flask.typing import ResponseReturnValue
 
+from abogen.domain.device import select_device as _select_device
+from abogen.domain.split_pattern import get_split_pattern
+
 
-SPLIT_PATTERN = r"\n+"
 SAMPLE_RATE = 24000
 
 _preview_pipelines: Dict[Tuple[str, str], Any] = {}
 _preview_pipeline_lock = threading.Lock()
 
 
-def _select_device() -> str:
+def clear_preview_pipelines() -> None:
-    import platform
+    """Dispose all cached preview pipelines and clear the cache."""
-
+    with _preview_pipeline_lock:
-    system = platform.system()
+        for pipeline in _preview_pipelines.values():
-    if system == "Darwin" and platform.processor() == "arm":
-        return "mps"
-    return "cuda"
-
-
-def _to_float32(audio_segment) -> np.ndarray:
-    if audio_segment is None:
-        return np.zeros(0, dtype="float32")
-
-    tensor = audio_segment
-    if hasattr(tensor, "detach"):
-        tensor = tensor.detach()
-    if hasattr(tensor, "cpu"):
             try:
-            tensor = tensor.cpu()
+                pipeline.dispose()
             except Exception:
                 pass
-    if hasattr(tensor, "numpy"):
+        _preview_pipelines.clear()
-        return np.asarray(tensor.numpy(), dtype="float32").reshape(-1)
+
-    return np.asarray(tensor, dtype="float32").reshape(-1)
+
+def _resolve_pipeline(language: str, use_gpu: bool) -> Tuple[Any, bool]:
+    devices: List[str] = ["cpu"]
+    if use_gpu:
+        preferred = _select_device()
+        if preferred != "cpu":
+            devices.insert(0, preferred)
+
+    last_error: Optional[Exception] = None
+    for device in devices:
+        try:
+            return get_preview_pipeline(language, device), device != "cpu"
+        except Exception as exc:
+            last_error = exc
+
+    raise RuntimeError("Preview pipeline is unavailable") from last_error
+
 
 def get_preview_pipeline(language: str, device: str) -> Any:
     key = (language, device)
@@ -45,10 +50,9 @@ def get_preview_pipeline(language: str, device: str) -> Any:
         pipeline = _preview_pipelines.get(key)
         if pipeline is not None:
             return pipeline
-        from abogen.utils import load_numpy_kpipeline
+        from abogen.tts_plugin.utils import create_pipeline
 
-        _, KPipeline = load_numpy_kpipeline()
+        pipeline = create_pipeline("kokoro", lang_code=language, device=device)
-        pipeline = KPipeline(lang_code=language, repo_id="hexgrad/Kokoro-82M", device=device)
         _preview_pipelines[key] = pipeline
         return pipeline
 
@@ -103,27 +107,21 @@ def generate_preview_audio(
             current_app.logger.exception("Preview normalization failed; using raw text")
             normalized_text = source_text
 
-    if provider == "supertonic":
+    preview_split = get_split_pattern(str(language or "a"), "Disabled")
-        from abogen.tts_supertonic import SupertonicPipeline
 
-        pipeline = SupertonicPipeline(sample_rate=SAMPLE_RATE, auto_download=True, total_steps=supertonic_total_steps)
+    if provider == "supertonic":
+        from abogen.tts_plugin.utils import create_pipeline
+
+        pipeline = create_pipeline("supertonic")
         segments = pipeline(
             normalized_text,
             voice=voice_spec,
             speed=speed,
-            split_pattern=SPLIT_PATTERN,
+            split_pattern=preview_split,
             total_steps=supertonic_total_steps,
         )
     else:
-        device = "cpu"
+        pipeline, pipeline_uses_gpu = _resolve_pipeline(language, use_gpu)
-        if use_gpu:
-            try:
-                device = _select_device()
-            except Exception:
-                device = "cpu"
-                use_gpu = False
-
-        pipeline = get_preview_pipeline(language, device)
         if pipeline is None:
             raise RuntimeError("Preview pipeline is unavailable")
 
@@ -131,13 +129,13 @@ def generate_preview_audio(
         if voice_spec and "*" in voice_spec:
             from abogen.voice_formulas import get_new_voice
 
-            voice_choice = get_new_voice(pipeline, voice_spec, use_gpu)
+            voice_choice = get_new_voice(pipeline, voice_spec, pipeline_uses_gpu)
 
         segments = pipeline(
             normalized_text,
             voice=voice_choice,
             speed=speed,
-            split_pattern=SPLIT_PATTERN,
+            split_pattern=preview_split,
         )
 
     audio_chunks: List[np.ndarray] = []

abogen/webui/routes/utils/voice.py

@@ -1,6 +1,4 @@
-import threading
 from typing import Any, Dict, Iterable, List, Mapping, Optional, Tuple, cast
-import numpy as np
 
 from abogen.speaker_configs import slugify_label
 from abogen.speaker_analysis import analyze_speakers
@@ -10,21 +8,17 @@ from abogen.voice_profiles import (
     load_profiles,
     serialize_profiles,
 )
-from abogen.voice_formulas import get_new_voice, parse_formula_terms
+from abogen.voice_formulas import parse_formula_terms
 from abogen.constants import (
     LANGUAGE_DESCRIPTIONS,
     SUBTITLE_FORMATS,
     SUPPORTED_SOUND_FORMATS,
     SUPPORTED_LANGUAGES_FOR_SUBTITLE_GENERATION,
     SAMPLE_VOICE_TEXTS,
-    VOICES_INTERNAL,
 )
+from abogen.tts_plugin.utils import get_voices
 from abogen.speaker_configs import list_configs
-from abogen.utils import load_numpy_kpipeline
-from abogen.webui.conversion_runner import _select_device, _to_float32, SAMPLE_RATE, SPLIT_PATTERN
 
-_preview_pipeline_lock = threading.RLock()
-_preview_pipelines: Dict[Tuple[str, str], Any] = {}
 
 def build_narrator_roster(
     voice: str,
@@ -285,7 +279,7 @@ def filter_voice_catalog(
 def build_voice_catalog() -> List[Dict[str, str]]:
     catalog: List[Dict[str, str]] = []
     gender_map = {"f": "Female", "m": "Male"}
-    for voice_id in VOICES_INTERNAL:
+    for voice_id in get_voices("kokoro"):
         prefix, _, rest = voice_id.partition("_")
         language_code = prefix[0] if prefix else "a"
         gender_code = prefix[1] if len(prefix) > 1 else ""
@@ -554,19 +548,12 @@ def prepare_speaker_metadata(
 
 
 def formula_from_profile(entry: Dict[str, Any]) -> Optional[str]:
+    from abogen.voice_formulas import pairs_to_formula
+
     voices = entry.get("voices") or []
     if not voices:
         return None
-    total = sum(weight for _, weight in voices)
+    return pairs_to_formula(voices)
-    if total <= 0:
-        return None
-
-    def _format_weight(value: float) -> str:
-        normalized = value / total if total else 0.0
-        return (f"{normalized:.4f}").rstrip("0").rstrip(".") or "0"
-
-    parts = [f"{name}*{_format_weight(weight)}" for name, weight in voices if weight > 0]
-    return "+".join(parts) if parts else None
 
 
 def template_options() -> Dict[str, Any]:
@@ -590,7 +577,7 @@ def template_options() -> Dict[str, Any]:
     voice_catalog = build_voice_catalog()
     return {
         "languages": LANGUAGE_DESCRIPTIONS,
-        "voices": VOICES_INTERNAL,
+        "voices": get_voices("kokoro"),
         "subtitle_formats": SUBTITLE_FORMATS,
         "supported_langs_for_subs": SUPPORTED_LANGUAGES_FOR_SUBTITLE_GENERATION,
         "output_formats": SUPPORTED_SOUND_FORMATS,
@@ -716,94 +703,9 @@ def sanitize_voice_entries(entries: Iterable[Any]) -> List[Dict[str, Any]]:
 
 
 def pairs_to_formula(pairs: Iterable[Tuple[str, float]]) -> Optional[str]:
-    voices = [(voice, float(weight)) for voice, weight in pairs if float(weight) > 0]
+    from abogen.voice_formulas import pairs_to_formula as _pairs_to_formula
-    if not voices:
+    return _pairs_to_formula(pairs)
-        return None
-    total = sum(weight for _, weight in voices)
-    if total <= 0:
-        return None
-
-    def _format_value(value: float) -> str:
-        normalized = value / total if total else 0.0
-        return (f"{normalized:.4f}").rstrip("0").rstrip(".") or "0"
-
-    parts = [f"{voice}*{_format_value(weight)}" for voice, weight in voices]
-    return "+".join(parts)
 
 
 def profiles_payload() -> Dict[str, Any]:
     return {"profiles": serialize_profiles()}
-
-
-def get_preview_pipeline(language: str, device: str):
-    key = (language, device)
-    with _preview_pipeline_lock:
-        pipeline = _preview_pipelines.get(key)
-        if pipeline is not None:
-            return pipeline
-        _, KPipeline = load_numpy_kpipeline()
-        pipeline = KPipeline(lang_code=language, repo_id="hexgrad/Kokoro-82M", device=device)
-        _preview_pipelines[key] = pipeline
-        return pipeline
-
-
-def synthesize_audio_from_normalized(
-    *,
-    normalized_text: str,
-    voice_spec: str,
-    language: str,
-    speed: float,
-    use_gpu: bool,
-    max_seconds: float,
-) -> np.ndarray:
-    if not normalized_text.strip():
-        raise ValueError("Preview text is required")
-
-    device = "cpu"
-    if use_gpu:
-        try:
-            device = _select_device()
-        except Exception:
-            device = "cpu"
-            use_gpu = False
-
-    pipeline = get_preview_pipeline(language, device)
-    if pipeline is None:
-        raise RuntimeError("Preview pipeline is unavailable")
-
-    voice_choice: Any = voice_spec
-    if voice_spec and "*" in voice_spec:
-        voice_choice = get_new_voice(pipeline, voice_spec, use_gpu)
-
-    segments = pipeline(
-        normalized_text,
-        voice=voice_choice,
-        speed=speed,
-        split_pattern=SPLIT_PATTERN,
-    )
-
-    audio_chunks: List[np.ndarray] = []
-    accumulated = 0
-    max_samples = int(max(1.0, max_seconds) * SAMPLE_RATE)
-
-    for segment in segments:
-        graphemes = getattr(segment, "graphemes", "").strip()
-        if not graphemes:
-            continue
-        audio = _to_float32(getattr(segment, "audio", None))
-        if audio.size == 0:
-            continue
-        remaining = max_samples - accumulated
-        if remaining <= 0:
-            break
-        if audio.shape[0] > remaining:
-            audio = audio[:remaining]
-        audio_chunks.append(audio)
-        accumulated += audio.shape[0]
-        if accumulated >= max_samples:
-            break
-
-    if not audio_chunks:
-        raise RuntimeError("Preview could not be generated")
-
-    return np.concatenate(audio_chunks)

abogen/webui/routes/voices.py

@@ -9,7 +9,7 @@ from abogen.webui.routes.utils.voice import (
     parse_voice_formula,
 )
 from abogen.webui.routes.utils.settings import load_settings, coerce_bool
-from abogen.webui.routes.utils.preview import synthesize_preview
+from abogen.webui.routes.utils.synthesize import synthesize_preview
 from abogen.speaker_configs import (
     list_configs,
     get_config,
@@ -17,7 +17,7 @@ from abogen.speaker_configs import (
     save_configs,
     delete_config,
 )
-from abogen.constants import VOICES_INTERNAL
+
 
 voices_bp = Blueprint("voices", __name__)
 

abogen/webui/service.py

@@ -2,9 +2,7 @@ from __future__ import annotations
 
 import json
 import logging
-import math
 import os
-import re
 import shutil
 import sys
 import threading
@@ -14,7 +12,7 @@ import traceback
 from dataclasses import dataclass, field
 from enum import Enum
 from pathlib import Path
-from typing import Any, Callable, Dict, Iterable, List, Optional, Mapping, Tuple
+from typing import Any, Callable, Dict, Iterable, List, Optional, Mapping
 
 from abogen.utils import get_internal_cache_path, get_user_settings_dir, load_config
 from abogen.voice_cache import bootstrap_voice_cache
@@ -23,6 +21,17 @@ from abogen.integrations.audiobookshelf import (
     AudiobookshelfConfig,
     AudiobookshelfUploadError,
 )
+from abogen.domain.metadata_helpers import (
+    normalize_metadata_casefold as _normalize_metadata_casefold,
+    split_people_field as _split_people_field,
+    split_simple_list as _split_simple_list,
+    first_nonempty as _first_nonempty,
+    extract_year as _extract_year,
+    normalize_series_sequence as _normalize_series_sequence,
+    build_audiobookshelf_metadata as _build_abs_metadata,
+    load_audiobookshelf_chapters as _load_abs_chapters,
+    _SERIES_SEQUENCE_TAG_KEYS,
+)
 
 
 def _create_set_event() -> threading.Event:
@@ -53,9 +62,6 @@ _JOB_LEVEL_MAP: Dict[str, int] = {
 }
 
 
-_PEOPLE_SPLIT_RE = re.compile(r"[;,/&]|\band\b", re.IGNORECASE)
-
-
 def _emit_job_log(job_id: str, level: str, message: str) -> None:
     normalized = (level or "info").lower()
     log_level = _JOB_LEVEL_MAP.get(normalized, logging.INFO)
@@ -131,6 +137,7 @@ class Job:
     progress: float = 0.0
     total_characters: int = 0
     processed_characters: int = 0
+    etr_str: str = ""
     logs: List[JobLog] = field(default_factory=list)
     error: Optional[str] = None
     result: JobResult = field(default_factory=JobResult)
@@ -162,20 +169,25 @@ class Job:
     @property
     def estimated_time_remaining(self) -> Optional[float]:
         """
-        Returns the estimated seconds remaining based on current progress and elapsed time.
+        Returns the estimated seconds remaining.
-        Returns None if the job hasn't started, is finished, or progress is 0.
+        Uses the same calc_etr_str from domain/progress.py as the PyQt desktop GUI.
         """
-        if self.status != JobStatus.RUNNING or not self.started_at or self.progress <= 0:
+        from abogen.domain.progress import calc_etr_str
+
+        if self.status != JobStatus.RUNNING or not self.started_at or self.total_characters <= 0:
             return None
 
         elapsed = time.time() - self.started_at
         if elapsed <= 0:
             return None
 
-        # Estimate total time based on current progress
+        etr = calc_etr_str(elapsed, self.processed_characters, self.total_characters)
-        total_estimated = elapsed / self.progress
+        if etr == "Processing...":
-        remaining = total_estimated - elapsed
+            return None
-        return max(0.0, remaining)
+
+        # Parse "HH:MM:SS" back to seconds for backward compatibility
+        parts = etr.split(":")
+        return int(parts[0]) * 3600 + int(parts[1]) * 60 + int(parts[2])
 
     def add_log(self, message: str, level: str = "info") -> None:
         entry = JobLog(timestamp=time.time(), message=message, level=level)
@@ -194,6 +206,7 @@ class Job:
             "progress": self.progress,
             "total_characters": self.total_characters,
             "processed_characters": self.processed_characters,
+            "etr_str": self.etr_str,
             "error": self.error,
             "logs": [log.__dict__ for log in self.logs],
             "result": {
@@ -252,234 +265,13 @@ class Job:
         }
 
 
-def _normalize_metadata_casefold(values: Optional[Mapping[str, Any]]) -> Dict[str, Any]:
-    normalized: Dict[str, Any] = {}
-    if not values:
-        return normalized
-    for key, value in values.items():
-        if value is None:
-            continue
-        key_text = str(key).strip().lower()
-        if not key_text:
-            continue
-        if isinstance(value, (list, tuple, set)):
-            normalized[key_text] = value
-        else:
-            text = str(value).strip()
-            if text:
-                normalized[key_text] = text
-    return normalized
-
-
-def _split_people_field(raw: Any) -> List[str]:
-    if raw is None:
-        return []
-    if isinstance(raw, (list, tuple, set)):
-        results: List[str] = []
-        for item in raw:
-            results.extend(_split_people_field(item))
-        return results
-    text = str(raw or "").strip()
-    if not text:
-        return []
-    tokens = [_token.strip() for _token in _PEOPLE_SPLIT_RE.split(text) if _token.strip()]
-    seen: set[str] = set()
-    ordered: List[str] = []
-    for token in tokens:
-        key = token.casefold()
-        if key in seen:
-            continue
-        seen.add(key)
-        ordered.append(token)
-    return ordered
-
-
-_LIST_SPLIT_RE = re.compile(r"[;,\n]")
-_SERIES_SEQUENCE_NUMBER_RE = re.compile(r"\d+(?:\.\d+)?")
-
-_SERIES_SEQUENCE_TAG_KEYS: Tuple[str, ...] = (
-    "series_index",
-    "series_position",
-    "series_sequence",
-    "series_number",
-    "seriesnumber",
-    "book_number",
-    "booknumber",
-)
-
-
-def _split_simple_list(raw: Any) -> List[str]:
-    if raw is None:
-        return []
-    if isinstance(raw, (list, tuple, set)):
-        results: List[str] = []
-        for item in raw:
-            results.extend(_split_simple_list(item))
-        return results
-    text = str(raw or "").strip()
-    if not text:
-        return []
-    tokens = [_token.strip() for _token in _LIST_SPLIT_RE.split(text) if _token.strip()]
-    seen: set[str] = set()
-    ordered: List[str] = []
-    for token in tokens:
-        key = token.casefold()
-        if key in seen:
-            continue
-        seen.add(key)
-        ordered.append(token)
-    return ordered
-
-
-def _first_nonempty(*values: Any) -> Optional[str]:
-    for value in values:
-        if value is None:
-            continue
-        if isinstance(value, (list, tuple, set)):
-            items = list(value)
-            if not items:
-                continue
-            value = items[0]
-        text = str(value).strip()
-        if text:
-            return text
-    return None
-
-
-def _extract_year(raw: Optional[str]) -> Optional[int]:
-    if not raw:
-        return None
-    text = str(raw).strip()
-    if not text:
-        return None
-    match = re.search(r"(19|20)\d{2}", text)
-    if match:
-        try:
-            return int(match.group(0))
-        except ValueError:
-            return None
-    try:
-        parsed = int(text)
-    except ValueError:
-        return None
-    if 0 < parsed < 3000:
-        return parsed
-    return None
-
-
 def build_audiobookshelf_metadata(job: Job) -> Dict[str, Any]:
-    tags = _normalize_metadata_casefold(job.metadata_tags)
     filename = Path(job.original_filename or "").stem or job.original_filename or "Audiobook"
-    title = _first_nonempty(
+    return _build_abs_metadata(
-        tags.get("title"),
+        job.metadata_tags,
-        tags.get("book_title"),
+        language=job.language or "",
-        tags.get("name"),
+        filename=filename,
-        tags.get("album"),
-        filename,
     )
-    authors = _split_people_field(
-        tags.get("authors")
-        or tags.get("author")
-        or tags.get("album_artist")
-        or tags.get("artist")
-    )
-    narrators = _split_people_field(tags.get("narrators") or tags.get("narrator"))
-    description = _first_nonempty(tags.get("description"), tags.get("summary"), tags.get("comment"))
-    genres = _split_simple_list(tags.get("genre"))
-    keywords = _split_simple_list(tags.get("tags") or tags.get("keywords"))
-    language = _first_nonempty(tags.get("language"), tags.get("lang")) or job.language or ""
-    series_name = _first_nonempty(
-        tags.get("series"),
-        tags.get("series_name"),
-        tags.get("seriesname"),
-        tags.get("series_title"),
-        tags.get("seriestitle"),
-    )
-    
-    series_sequence = None
-    for key in _SERIES_SEQUENCE_TAG_KEYS:
-        raw_value = tags.get(key)
-        normalized_sequence = _normalize_series_sequence(raw_value)
-        if normalized_sequence:
-            series_sequence = normalized_sequence
-            break
-    if not series_name:
-        series_sequence = None
-    data: Dict[str, Any] = {
-        "title": title,
-        "subtitle": tags.get("subtitle"),
-        "authors": authors,
-        "narrators": narrators,
-        "description": description,
-        "publisher": tags.get("publisher"),
-        "genres": genres,
-        "tags": keywords,
-        "language": language,
-        "publishedYear": _extract_year(tags.get("published") or tags.get("publication_year") or tags.get("date") or tags.get("year")),
-        "seriesName": series_name,
-        "seriesSequence": series_sequence,
-        "isbn": _first_nonempty(tags.get("isbn"), tags.get("asin")),
-    }
-    published_date = _first_nonempty(tags.get("published"), tags.get("publication_date"), tags.get("date"))
-    if published_date:
-        data["publishedDate"] = published_date
-
-    rating_text = _first_nonempty(tags.get("rating"), tags.get("my_rating"))
-    if rating_text:
-        try:
-            data["rating"] = float(str(rating_text).strip())
-        except ValueError:
-            pass
-        rating_max_text = _first_nonempty(tags.get("rating_max"), tags.get("rating_scale"))
-        if rating_max_text:
-            try:
-                data["ratingMax"] = float(str(rating_max_text).strip())
-            except ValueError:
-                pass
-    # Remove empty values
-    cleaned: Dict[str, Any] = {}
-    for key, value in data.items():
-        if value is None:
-            continue
-        if isinstance(value, str) and not value.strip():
-            continue
-        if isinstance(value, (list, tuple)) and not value:
-            continue
-        cleaned[key] = value
-    return cleaned
-
-
-def _normalize_series_sequence(raw: Any) -> Optional[str]:
-    if raw is None:
-        return None
-
-    if isinstance(raw, (int, float)):
-        if isinstance(raw, float) and (math.isnan(raw) or math.isinf(raw)):
-            return None
-        text = str(raw)
-    else:
-        text = str(raw).strip()
-
-    if not text:
-        return None
-
-    candidate = text.replace(",", ".")
-    match = _SERIES_SEQUENCE_NUMBER_RE.search(candidate)
-    if not match:
-        return None
-
-    normalized = match.group(0)
-    if "." in normalized:
-        normalized = normalized.rstrip("0").rstrip(".")
-        if not normalized:
-            normalized = "0"
-        return normalized
-
-    try:
-        return str(int(normalized))
-    except ValueError:
-        cleaned = normalized.lstrip("0")
-        return cleaned or "0"
 
 
 def load_audiobookshelf_chapters(job: Job) -> Optional[List[Dict[str, Any]]]:
@@ -487,32 +279,7 @@ def load_audiobookshelf_chapters(job: Job) -> Optional[List[Dict[str, Any]]]:
     if not metadata_ref:
         return None
     metadata_path = metadata_ref if isinstance(metadata_ref, Path) else Path(str(metadata_ref))
-    if not metadata_path.exists():
+    return _load_abs_chapters(metadata_path)
-        return None
-    try:
-        payload = json.loads(metadata_path.read_text(encoding="utf-8"))
-    except (OSError, json.JSONDecodeError):
-        return None
-    chapters = payload.get("chapters")
-    if not isinstance(chapters, list):
-        return None
-    cleaned: List[Dict[str, Any]] = []
-    for entry in chapters:
-        if not isinstance(entry, Mapping):
-            continue
-        title = _first_nonempty(entry.get("title"), entry.get("original_title"))
-        start = entry.get("start")
-        end = entry.get("end")
-        if title is None or not isinstance(start, (int, float)):
-            continue
-        chapter_payload: Dict[str, Any] = {
-            "title": title,
-            "start": float(start),
-        }
-        if isinstance(end, (int, float)):
-            chapter_payload["end"] = float(end)
-        cleaned.append(chapter_payload)
-    return cleaned or None
 
 
 def _existing_paths(paths: Iterable[Any]) -> List[Path]:
@@ -1609,10 +1376,12 @@ def build_service(
     output_root: Optional[Path] = None,
     uploads_root: Optional[Path] = None,
 ) -> ConversionService:
+    global _service_instance
     output_root = output_root or default_storage_root()
     service = ConversionService(
         output_root=output_root,
         uploads_root=uploads_root,
         runner=runner,
     )
+    _service_instance = service
     return service

abogen/webui/services/settings_service.py

@@ -0,0 +1,165 @@
+"""Settings form-to-dict mapping.
+
+Pure functions that convert form data into a settings dict.
+No Flask dependencies — testable without a request context.
+"""
+
+from __future__ import annotations
+
+from collections.abc import Mapping
+from typing import Any
+
+
+def apply_form_to_settings(current: dict, form: Mapping[str, Any]) -> dict:
+    """Apply form data to a settings dict.
+
+    Pure function: takes a current settings dict and a form-like mapping,
+    returns the updated settings dict. No Flask dependencies.
+
+    Args:
+        current: Current settings dict (will be mutated).
+        form: Form-like mapping (e.g. request.form.to_dict()).
+
+    Returns:
+        Updated settings dict (same object as input).
+    """
+    from abogen.domain.settings_core import (
+        coerce_bool,
+        coerce_int,
+        DEFAULT_ANALYSIS_THRESHOLD,
+        _NORMALIZATION_BOOLEAN_KEYS,
+        _NORMALIZATION_STRING_KEYS,
+    )
+    from abogen.webui.routes.utils.settings import stored_integration_config
+    from abogen.webui.routes.utils.common import extract_checkbox
+    from abogen.utils import load_config
+    # General settings
+    current["language"] = (form.get("language") or "en").strip()
+    current["default_speaker"] = (form.get("default_speaker") or "").strip()
+    current["default_voice"] = (form.get("default_voice") or "").strip()
+    try:
+        current["supertonic_total_steps"] = max(2, min(15, int(form.get("supertonic_total_steps", current.get("supertonic_total_steps", 5)))))
+    except (TypeError, ValueError):
+        pass
+    try:
+        current["supertonic_speed"] = max(0.7, min(2.0, float(form.get("supertonic_speed", current.get("supertonic_speed", 1.0)))))
+    except (TypeError, ValueError):
+        pass
+    current["output_format"] = (form.get("output_format") or "mp3").strip()
+    current["subtitle_mode"] = (form.get("subtitle_mode") or "Disabled").strip()
+    current["subtitle_format"] = (form.get("subtitle_format") or "srt").strip()
+    current["save_mode"] = (form.get("save_mode") or "save_next_to_input").strip()
+
+    current["replace_single_newlines"] = coerce_bool(form.get("replace_single_newlines"), False)
+    current["use_gpu"] = coerce_bool(form.get("use_gpu"), False)
+    current["save_chapters_separately"] = coerce_bool(form.get("save_chapters_separately"), False)
+    current["merge_chapters_at_end"] = coerce_bool(form.get("merge_chapters_at_end"), True)
+    current["save_as_project"] = coerce_bool(form.get("save_as_project"), False)
+    current["separate_chapters_format"] = (form.get("separate_chapters_format") or "wav").strip()
+
+    try:
+        current["silence_between_chapters"] = max(0.0, float(form.get("silence_between_chapters", 2.0)))
+    except ValueError:
+        pass
+
+    try:
+        current["chapter_intro_delay"] = max(0.0, float(form.get("chapter_intro_delay", 0.5)))
+    except ValueError:
+        pass
+
+    current["read_title_intro"] = coerce_bool(form.get("read_title_intro"), False)
+    current["read_closing_outro"] = coerce_bool(form.get("read_closing_outro"), True)
+    current["normalize_chapter_opening_caps"] = coerce_bool(form.get("normalize_chapter_opening_caps"), True)
+    current["auto_prefix_chapter_titles"] = coerce_bool(form.get("auto_prefix_chapter_titles"), True)
+
+    try:
+        current["max_subtitle_words"] = max(1, int(form.get("max_subtitle_words", 50)))
+    except ValueError:
+        pass
+
+    current["chunk_level"] = (form.get("chunk_level") or "paragraph").strip()
+    current["generate_epub3"] = coerce_bool(form.get("generate_epub3"), False)
+
+    current["speaker_analysis_threshold"] = coerce_int(
+        form.get("speaker_analysis_threshold"),
+        DEFAULT_ANALYSIS_THRESHOLD,
+        minimum=1,
+        maximum=25,
+    )
+
+    # Normalization settings
+    for key in _NORMALIZATION_BOOLEAN_KEYS:
+        current[key] = extract_checkbox(form, key, bool(current.get(key, True)))
+    for key in _NORMALIZATION_STRING_KEYS:
+        if key in form:
+            current[key] = (form.get(key) or "").strip()
+
+    # Integrations — seed from stored config to prevent wiping credentials
+    current_integrations: dict[str, dict[str, Any]] = {}
+    cfg = load_config() or {}
+    stored_integrations = cfg.get("integrations")
+    if isinstance(stored_integrations, Mapping):
+        for name, payload in stored_integrations.items():
+            if isinstance(name, str) and isinstance(payload, Mapping):
+                current_integrations[name] = dict(payload)
+    for name in ("audiobookshelf", "calibre_opds"):
+        stored = stored_integration_config(name)
+        if stored and name not in current_integrations:
+            current_integrations[name] = dict(stored)
+    current["integrations"] = current_integrations
+
+    # Audiobookshelf
+    abs_enabled = coerce_bool(form.get("audiobookshelf_enabled"), False)
+    abs_url = (form.get("audiobookshelf_base_url") or "").strip()
+    abs_token = (form.get("audiobookshelf_api_token") or "").strip()
+    abs_library = (form.get("audiobookshelf_library_id") or "").strip()
+    abs_folder = (form.get("audiobookshelf_folder_id") or "").strip()
+    abs_verify = coerce_bool(form.get("audiobookshelf_verify_ssl"), True)
+    abs_auto_send = coerce_bool(form.get("audiobookshelf_auto_send"), False)
+    abs_cover = coerce_bool(form.get("audiobookshelf_send_cover"), True)
+    abs_chapters = coerce_bool(form.get("audiobookshelf_send_chapters"), True)
+    abs_subtitles = coerce_bool(form.get("audiobookshelf_send_subtitles"), False)
+
+    try:
+        abs_timeout = max(1.0, float(form.get("audiobookshelf_timeout", 30.0)))
+    except ValueError:
+        abs_timeout = 30.0
+
+    if not abs_token and not coerce_bool(form.get("audiobookshelf_api_token_clear"), False):
+        existing_abs = current["integrations"].get("audiobookshelf", {})
+        abs_token = existing_abs.get("api_token", "")
+
+    current["integrations"]["audiobookshelf"] = {
+        "enabled": abs_enabled,
+        "base_url": abs_url,
+        "api_token": abs_token,
+        "library_id": abs_library,
+        "folder_id": abs_folder,
+        "verify_ssl": abs_verify,
+        "auto_send": abs_auto_send,
+        "send_cover": abs_cover,
+        "send_chapters": abs_chapters,
+        "send_subtitles": abs_subtitles,
+        "timeout": abs_timeout,
+    }
+
+    # Calibre OPDS
+    calibre_enabled = coerce_bool(form.get("calibre_opds_enabled"), False)
+    calibre_url = (form.get("calibre_opds_base_url") or "").strip()
+    calibre_user = (form.get("calibre_opds_username") or "").strip()
+    calibre_pass = (form.get("calibre_opds_password") or "").strip()
+    calibre_verify = coerce_bool(form.get("calibre_opds_verify_ssl"), True)
+
+    if not calibre_pass and not coerce_bool(form.get("calibre_opds_password_clear"), False):
+        existing_calibre = current["integrations"].get("calibre_opds", {})
+        calibre_pass = existing_calibre.get("password", "")
+
+    current["integrations"]["calibre_opds"] = {
+        "enabled": calibre_enabled,
+        "base_url": calibre_url,
+        "username": calibre_user,
+        "password": calibre_pass,
+        "verify_ssl": calibre_verify,
+    }
+
+    return current

abogen/webui/templates/partials/jobs.html

@@ -28,8 +28,8 @@
             </div>
             <div class="job-card__progress-meta">
               <small>{{ progress_value }}% · {{ job.processed_characters }} / {{ job.total_characters or '—' }}</small>
-              {% if job.estimated_time_remaining %}
+              {% if job.etr_str and job.etr_str != 'Processing...' %}
-                <small class="job-card__eta">~{{ job.estimated_time_remaining | durationformat }} remaining</small>
+                <small class="job-card__eta">~{{ job.etr_str }} remaining</small>
               {% endif %}
             </div>
           </div>

abogen/word_substitution.py

@@ -0,0 +1,254 @@
+"""
+Word substitution module for text-to-speech preprocessing.
+
+This module provides functionality to:
+- Replace words/phrases with custom text
+- Convert ALL CAPS to lowercase
+- Convert numerals to words
+- Fix nonstandard punctuation for TTS compatibility
+
+All substitutions preserve special markers (chapter, voice, metadata, timestamps).
+"""
+
+import re
+
+from abogen.subtitle_utils import (
+    _CHAPTER_MARKER_PATTERN,
+    _VOICE_MARKER_PATTERN,
+    _METADATA_TAG_PATTERN,
+    _TIMESTAMP_ONLY_PATTERN,
+)
+
+
+def apply_word_substitutions(
+    text,
+    substitutions_list_str,
+    case_sensitive=False,
+    replace_all_caps=False,
+    replace_numerals=False,
+    fix_nonstandard_punctuation=False,
+):
+    """
+    Apply word substitutions to text while preserving markers.
+
+    Args:
+        text: Input text
+        substitutions_list_str: Newline-separated "Word|NewWord" pairs
+        case_sensitive: If True, match words case-sensitively
+        replace_all_caps: Convert ALL CAPS words to lowercase
+        replace_numerals: Convert numbers to words
+        fix_nonstandard_punctuation: Fix curly quotes, em/en dashes, etc.
+
+    Returns:
+        Modified text
+    """
+    # Apply nonstandard punctuation fixes FIRST (if enabled)
+    if fix_nonstandard_punctuation:
+        text = fix_punctuation(text)
+
+    # Parse substitutions list
+    substitutions = parse_substitutions_list(substitutions_list_str)
+
+    # Split text into segments (markers vs content)
+    segments = split_text_preserving_markers(text)
+
+    # Process each segment
+    processed_segments = []
+    for segment_type, segment_text in segments:
+        if segment_type == "marker":
+            # Preserve markers unchanged
+            processed_segments.append(segment_text)
+        else:
+            # Apply substitutions to content
+            processed_text = segment_text
+
+            # Apply word substitutions
+            if substitutions:
+                processed_text = apply_word_replacements(
+                    processed_text, substitutions, case_sensitive
+                )
+
+            # Apply ALL CAPS conversion
+            if replace_all_caps:
+                processed_text = convert_all_caps_to_lowercase(processed_text)
+
+            # Apply numeral conversion
+            if replace_numerals:
+                processed_text = convert_numerals_to_words(processed_text)
+
+            processed_segments.append(processed_text)
+
+    return "".join(processed_segments)
+
+
+def parse_substitutions_list(substitutions_str):
+    """
+    Parse newline-separated "Word|NewWord" format.
+
+    Args:
+        substitutions_str: String with substitutions, one per line
+
+    Returns:
+        List of tuples: [(word, replacement), ...]
+    """
+    substitutions = []
+    for line in substitutions_str.strip().split("\n"):
+        line = line.strip()
+        if not line or "|" not in line:
+            continue
+
+        parts = line.split("|", 1)
+        if len(parts) == 2:
+            word = parts[0].strip()
+            replacement = parts[1].strip()
+            if word:  # Only add if word is not empty
+                substitutions.append((word, replacement))
+
+    return substitutions
+
+
+def split_text_preserving_markers(text):
+    """
+    Split text into segments alternating between markers and content.
+
+    Args:
+        text: Input text with potential markers
+
+    Returns:
+        List of tuples: [("marker"|"content", text), ...]
+    """
+    # Combined pattern for all markers and timestamps
+    marker_pattern = re.compile(
+        r"(<<CHAPTER_MARKER:[^>]*>>|<<VOICE:[^>]*>>|<<METADATA_[^:]+:[^>]*>>|\d{1,2}:\d{2}:\d{2}(?:[.,]\d{1,3})?)"
+    )
+
+    segments = []
+    last_end = 0
+
+    for match in marker_pattern.finditer(text):
+        # Content before marker
+        if match.start() > last_end:
+            segments.append(("content", text[last_end : match.start()]))
+
+        # Marker itself
+        segments.append(("marker", match.group(0)))
+        last_end = match.end()
+
+    # Remaining content after last marker
+    if last_end < len(text):
+        segments.append(("content", text[last_end:]))
+
+    return segments
+
+
+def apply_word_replacements(text, substitutions, case_sensitive=False):
+    """
+    Apply word substitutions using whole-word matching.
+
+    Args:
+        text: Input text
+        substitutions: List of (word, replacement) tuples
+        case_sensitive: If True, match case-sensitively
+
+    Returns:
+        Text with substitutions applied
+    """
+    for word, replacement in substitutions:
+        # Use word boundaries for exact matching
+        # Escape special regex characters
+        escaped_word = re.escape(word)
+        pattern = re.compile(
+            r"\b" + escaped_word + r"\b",
+            0 if case_sensitive else re.IGNORECASE,
+        )
+        text = pattern.sub(replacement, text)
+
+    return text
+
+
+def convert_all_caps_to_lowercase(text):
+    """
+    Convert ALL CAPS words to lowercase.
+
+    Args:
+        text: Input text
+
+    Returns:
+        Text with ALL CAPS converted to lowercase
+    """
+
+    def replace_caps(match):
+        word = match.group(0)
+        # Convert to lowercase
+        return word.lower()
+
+    # Match words that are ALL CAPS (2+ letters)
+    pattern = re.compile(r"\b[A-Z]{2,}\b")
+    return pattern.sub(replace_caps, text)
+
+
+def convert_numerals_to_words(text):
+    """
+    Convert numerals to words using num2words library.
+
+    Args:
+        text: Input text
+
+    Returns:
+        Text with numerals converted to words
+    """
+    try:
+        from num2words import num2words
+    except ImportError:
+        # If num2words not available, return unchanged
+        return text
+
+    def replace_number(match):
+        try:
+            number = int(match.group(0))
+            # Convert to words in English
+            return num2words(number)
+        except Exception:
+            # If conversion fails, return original
+            return match.group(0)
+
+    # Match integers (but not timestamps or other patterns)
+    # Negative lookbehind/ahead to avoid timestamps
+    pattern = re.compile(r"(?<!\d:)\b\d+\b(?!:\d)")
+    return pattern.sub(replace_number, text)
+
+
+def fix_punctuation(text):
+    """
+    Convert nonstandard punctuation to standard equivalents.
+
+    This helps TTS engines pronounce words correctly by converting:
+    - Curly quotes to straight quotes
+    - Ellipsis to three periods
+
+    Args:
+        text: Input text
+
+    Returns:
+        Text with nonstandard punctuation fixed
+    """
+    # Define replacements
+    replacements = {
+        # Curly double quotes
+        "\u201c": '"',  # Left double quotation mark
+        "\u201d": '"',  # Right double quotation mark
+        "\u201e": '"',  # Double low-9 quotation mark
+        # Curly single quotes
+        "\u2018": "'",  # Left single quotation mark
+        "\u2019": "'",  # Right single quotation mark
+        "\u201a": "'",  # Single low-9 quotation mark
+        "\u201b": "'",  # Single high-reversed-9 quotation mark
+        # Other punctuation
+        "\u2026": "...",  # Ellipsis
+    }
+
+    # Apply all replacements
+    for old_char, new_char in replacements.items():
+        text = text.replace(old_char, new_char)
+
+    return text

docs/contributing.md

@@ -0,0 +1,55 @@
+# Contributing to Abogen
+
+We welcome contributions to Abogen!
+
+## How to Contribute
+
+1. Fork the repository
+2. Create a branch for your feature
+3. Make your changes
+4. Write tests
+5. Submit a pull request
+
+## Code Standards
+
+- Follow PEP 8 for Python
+- Use TypeScript for JavaScript
+- Type hints required for new Python code
+- Document complex logic with comments
+
+## Plugin Architecture
+
+When contributing TTS engines, implement the **Plugin Architecture** contract.
+
+See [Developer Guide](developer-guide.md#5-adding-a-new-plugin) for:
+- Required exports (`PLUGIN_MANIFEST`, `MODEL_REQUIREMENTS`, `create_engine`)
+- Engine / EngineSession contracts
+- Capability interfaces (`VoiceLister`, `PreviewGenerator`, etc.)
+- Step-by-step plugin creation guide
+
+## Testing
+
+```bash
+# All tests
+pytest
+
+# Contract tests (architectural compliance)
+pytest tests/contracts/
+
+# Behavioral regression tests
+pytest tests/test_behavioral_regression.py
+```
+
+## Documentation
+
+- Update relevant docs in `docs/` when changing architecture or APIs
+- Add docstrings to all public functions/classes
+- Follow existing documentation style
+
+## Pull Request Checklist
+
+- [ ] Tests pass (`pytest`)
+- [ ] Code follows style guide (`ruff check`, `ruff format`)
+- [ ] Documentation updated
+- [ ] No legacy architecture references (`TTSBackend`, `register_backend`, `TTSBackendRegistry`)
+- [ ] Uses new Plugin Architecture patterns

docs/developer-guide.md

@@ -0,0 +1,270 @@
+# TTS Plugin Architecture — Architectural Reference
+
+This document describes the **stable architectural contracts** of the TTS Plugin Architecture. It documents invariants that only change when the architecture itself changes.
+
+---
+
+## 1. Architecture Overview
+
+```
+┌─────────────────────────────────────────────────────────────────┐
+│                        Host Application                         │
+│  ┌─────────────┐  ┌──────────────┐  ┌────────────────────────┐  │
+│  │ Plugin      │  │ HostContext  │  │ Plugin Discovery       │  │
+│  │ Manager     │──│ (config_dir, │  │ (plugin directories)   │  │
+│  │             │  │  logger,     │  │                        │  │
+│  │ - discover  │  │  http_client)│  └────────────────────────┘  │
+│  │ - validate  │  └──────────────┘            │                 │
+│  │ - activate  │                              ▼                 │
+│  │ - dispose   │  ┌─────────────────────────────────────────┐   │
+│  └──────┬──────┘  │              Plugin Package             │   │
+│         │         │  ┌──────────────┐ ┌─────────────────┐   │   │
+│         ▼         │  │ PLUGIN_      │ │ MODEL_          │   │   │
+│  ┌────────────┐   │  │ MANIFEST     │ │ REQUIREMENTS    │   │   │
+│  │   Engine   │◄──┤  │ create_engine│ │                 │   │   │
+│  └──────┬─────┘   │  └──────────────┘ └─────────────────┘   │   │
+│         │         └─────────────────────────────────────────┘   │
+│         │ createSession()                                       │
+│         ▼                                                       │
+│  ┌─────────────┐                                                │
+│  │EngineSession│                                                │
+│  └──────┬──────┘                                                │
+│         │ synthesize()                                          │
+│         ▼                                                       │
+│  ┌────────────────┐                                             │
+│  │SynthesizedAudio│                                             │
+│  └────────────────┘                                             │
+└─────────────────────────────────────────────────────────────────┘
+```
+
+### Core Components
+
+| Component | Responsibility |
+|-----------|----------------|
+| **PluginManifest** | Static metadata: id, name, version, api_version, capabilities, engine manifest |
+| **EngineManifest** | Voice sources, parameters, audio formats |
+| **HostContext** | Minimal host services: config_dir, logger, http_client |
+| **Engine** | Stateless factory for sessions; thread-safe `createSession()` |
+| **EngineSession** | Owns mutable execution state; not thread-safe |
+| **PluginManager** | Discovers, validates, and manages plugin lifecycle |
+| **Capabilities** | Optional interfaces: VoiceLister, PreviewGenerator, StreamingSynthesizer, CancelableSession |
+
+---
+
+## 2. Ownership Model
+
+### Engine Ownership
+```
+PluginManager.create_engine() → Engine
+```
+- **PluginManager** creates and caches engines
+- **Caller** receives `Engine` instance
+- **Caller** must dispose all sessions **before** disposing engine
+- **Engine.dispose()** releases engine resources
+- After `Engine.dispose()`: all methods except `dispose()` raise `EngineError`
+
+### Session Ownership
+```
+Engine.createSession() → EngineSession
+```
+- **Engine** creates session
+- **Ownership transfers to caller** immediately
+- **Caller** is responsible for `session.dispose()`
+- **Engine does NOT track sessions** — no registry, no callbacks
+- After `session.dispose()`: all methods except `dispose()` raise `EngineError`
+
+### Disposal Order (Invariant)
+```python
+# Correct
+engine = manager.create_engine("id")
+session = engine.createSession()
+try:
+    audio = session.synthesize(request)
+finally:
+    session.dispose()      # 1. Sessions FIRST
+engine.dispose()           # 2. Then engine
+
+# INCORRECT — violates contract (undefined behavior)
+engine.dispose()
+session.synthesize(request)  # EngineError
+```
+
+---
+
+## 3. Lifecycle State Machine
+
+```
+DISCOVERY
+  PluginManager.discover(plugin_dirs)
+  → Loads PLUGIN_MANIFEST, MODEL_REQUIREMENTS
+  → Validates api_version (major must match)
+  → Validates declared capabilities are implemented
+
+MODEL_DOWNLOAD (if MODEL_REQUIREMENTS non-empty)
+  Host reads MODEL_REQUIREMENTS
+  Downloads/caches models
+  Resolves model_path
+
+ACTIVATION
+  create_engine(context, model_path, config)
+  → Atomic: succeeds fully or raises EngineError
+  → Returns Engine
+
+SESSION_CREATION
+  engine.createSession() → EngineSession
+  → Ownership transfers to caller
+  → Raises EngineError on failure
+  → Never returns partial session
+
+SYNTHESIS
+  session.synthesize(request)
+  → Returns SynthesizedAudio
+  → Raises EngineError on failure
+  → Session remains usable after error
+
+SESSION_DISPOSAL
+  session.dispose()
+  → Idempotent, never raises
+  → After: all methods raise EngineError
+
+DEACTIVATION
+  engine.dispose()
+  → Caller MUST dispose all sessions first
+  → Idempotent, never raises
+  → After: all methods raise EngineError
+```
+
+---
+
+## 4. Protocol Contracts
+
+### Engine (Protocol)
+```python
+@runtime_checkable
+class Engine(Protocol):
+    def createSession(self) -> EngineSession:
+        """Create a new session. Thread-safe. Transfers ownership."""
+        ...
+
+    def dispose(self) -> None:
+        """Release engine resources.
+        Caller must dispose all sessions first.
+        Idempotent, never raises.
+        After: all methods except dispose() raise EngineError."""
+        ...
+```
+
+### EngineSession (Protocol)
+```python
+@runtime_checkable
+class EngineSession(Protocol):
+    def synthesize(self, request: SynthesisRequest) -> SynthesizedAudio:
+        """Synthesize audio.
+        Returns SynthesizedAudio or raises EngineError.
+        Session remains usable after error."""
+        ...
+
+    def dispose(self) -> None:
+        """Release session resources.
+        Idempotent, never raises.
+        After: all methods except dispose() raise EngineError."""
+        ...
+```
+
+### Capability Protocols (Optional)
+- **VoiceLister**: `listVoices(source_id: str) -> list[VoiceManifest]`
+- **PreviewGenerator**: `generatePreview(voice: VoiceSelection, text: str) -> SynthesizedAudio`
+- **StreamingSynthesizer**: `synthesizeStream(request: SynthesisRequest) -> Iterator[bytes]`
+- **CancelableSession**: `cancel() -> None` (causes in-flight synthesize to raise `CancelledError`)
+
+---
+
+## 5. Error Semantics
+
+```
+EngineError (base)
+├── ModelNotFoundError      # Required model not found
+├── ModelLoadError          # Model failed to load
+├── NetworkError            # Network operation failed
+├── InvalidInputError       # Request validation failed
+├── ConfigurationError      # Invalid configuration
+├── CancelledError          # Operation cancelled via CancelableSession
+└── InternalError           # Unexpected internal failure
+```
+
+### When Each Is Raised
+| Error | Raised By | Conditions |
+|-------|-----------|------------|
+| `ModelNotFoundError` | `create_engine()` | Required model not found at `model_path` |
+| `ModelLoadError` | `create_engine()` | Model exists but fails to load |
+| `NetworkError` | `synthesize()`, `create_engine()` | Network call fails (cloud engines) |
+| `InvalidInputError` | `synthesize()` | Request validation fails (empty text, invalid voice, etc.) |
+| `ConfigurationError` | `create_engine()` | Config values invalid for this engine |
+| `CancelledError` | `synthesize()`, `synthesizeStream()` | `CancelableSession.cancel()` called |
+| `InternalError` | Any | Unexpected internal failure (bug) |
+
+### Dispose Contract
+- `dispose()` is **idempotent** and **never raises**
+- After `dispose()`: all methods except `dispose()` raise `EngineError`
+- Engine: caller must dispose all sessions first; violating this is undefined behavior
+
+---
+
+## 6. Capabilities
+
+| Capability | Interface | Enables |
+|------------|-----------|---------|
+| `voice_list` | `VoiceLister` | `listVoices(source_id)` — enumerate available voices |
+| `preview` | `PreviewGenerator` | `generatePreview(voice, text)` — preview without session |
+| `streaming` | `StreamingSynthesizer` | `synthesizeStream(request)` — chunked audio output |
+| `cancel` | `CancelableSession` | `cancel()` — interrupt in-flight synthesis |
+
+Plugins declare capabilities in `PluginManifest.capabilities`. Host validates at load time.
+
+---
+
+## 7. Contract Tests
+
+**Location**: `tests/contracts/`
+
+**Purpose**: Verify every plugin satisfies the architectural contracts.
+
+**Guarantees**:
+- Required exports exist (`PLUGIN_MANIFEST`, `MODEL_REQUIREMENTS`, `create_engine`)
+- `create_engine` is atomic
+- `Engine.createSession()` transfers ownership, never returns partial
+- `dispose()` is idempotent on Engine and EngineSession
+- After `dispose()`, methods raise `EngineError`
+- `synthesize()` raises typed `EngineError` subtypes, session remains usable
+- Declared capabilities are actually implemented
+- Plugin loader validates manifest, api_version, capabilities
+
+**Run**: `pytest tests/contracts/ -v`
+
+---
+
+## 8. Behavioral Tests
+
+**Location**: `tests/test_behavioral_regression.py`
+
+**Purpose**: Verify user-facing behavior via public API only (`create_pipeline`, `Engine`, `EngineSession`, `PluginManager`).
+
+**Scope**:
+- Synthesis with various inputs (short, long, empty, unicode, mixed scripts)
+- Voice selection and listing
+- Parameter handling (speed, etc.)
+- Error scenarios (unknown plugin, disposal, etc.)
+- Resource cleanup (dispose idempotency, no leaks)
+- Pipeline utility (`create_pipeline`)
+
+**Run**: `pytest tests/test_behavioral_regression.py -v`
+
+---
+
+## 9. Reference
+
+- **Architecture Spec**: `docs/architecture-final-v2.md`
+- **Amendment (lang_code)**: `docs/architecture-amendment-001.md`
+- **Migration Roadmap**: `docs/migration-roadmap.md`
+- **Plugin Examples**: `plugins/kokoro/`, `plugins/supertonic/`
+- **Protocol Definitions**: `abogen/tts_plugin/engine.py`, `abogen/tts_plugin/capabilities.py`

docs/getting-started.md

@@ -0,0 +1,68 @@
+# Getting Started
+
+Quickstart for developers working on Abogen.
+
+## Prerequisites
+
+- Python 3.10+
+- Node.js 20+
+- npm 10+
+- Git
+- Docker (optional)
+
+## Installation
+
+```bash
+# Development install with all extras
+pip install -e .[dev]
+
+# Or with uv
+uv pip install -e .[dev]
+```
+
+## Running the Application
+
+```bash
+# Desktop GUI
+abogen
+
+# Web UI
+abogen-web
+
+# CLI
+abogen-cli
+```
+
+## Project Structure
+
+```
+abogen/
+├── pyqt/         - PyQt6 desktop GUI
+├── webui/        - Flask web UI
+├── tts_plugin/   - Plugin Architecture (Engine, EngineSession, Manifest)
+└── plugins/      - Built-in plugins (kokoro, supertonic)
+tests/
+├── contracts/    - Contract compliance tests
+└── ...
+```
+
+## Testing
+
+```bash
+# All tests
+pytest
+
+# Contract tests (architectural compliance)
+pytest tests/contracts/
+
+# Behavioral regression tests
+pytest tests/test_behavioral_regression.py
+```
+
+## Architecture
+
+See [Developer Guide](developer-guide.md) for Plugin Architecture details:
+- Engine / EngineSession lifecycle
+- Plugin contract (PLUGIN_MANIFEST, create_engine)
+- Adding new plugins
+- Capability interfaces

docs/testing.md

@@ -0,0 +1,269 @@
+# Testing Guide
+
+This document describes the testing strategy for Abogen's Plugin Architecture.
+
+## Test Categories
+
+### 0. Auto-Discovery Plugin Tests (`tests/plugins/`)
+
+**Purpose**: Automatically test every plugin in `plugins/` directory without manual test creation. These tests use discovery to find all plugins and run generic tests against each one.
+
+**What They Test**:
+- **Manifest structure**: Required fields, API version format, voices field
+- **Engine lifecycle**: `create_engine`, `dispose` idempotency, post-dispose behavior
+- **Capability implementation**: Declared capabilities are implemented (e.g., `voice_list` → `VoiceLister`)
+
+**How Auto-Discovery Works**:
+```python
+# tests/plugins/conftest.py
+@pytest.fixture(scope="module")
+def plugin_ids(plugins_dir: Path) -> list[str]:
+    """Discovers all plugin directories with __init__.py"""
+    return [item.name for item in plugins_dir.iterdir() 
+            if item.is_dir() and (item / "__init__.py").exists()]
+```
+
+**Test Structure**:
+```
+tests/plugins/
+├── conftest.py              # Fixtures: plugin_ids, loaded_plugin, host_context
+└── test_all_plugins.py      # Generic tests for every plugin
+    ├── TestAllPluginsManifest
+    ├── TestAllPluginsEngine
+    └── TestAllPluginsCapabilities
+```
+
+**Running Auto-Discovery Tests**:
+```bash
+# Test all plugins automatically
+pytest tests/plugins/ -v
+
+# Test specific plugin
+pytest tests/plugins/ -v -k "kokoro"
+
+# See which plugins were discovered
+pytest tests/plugins/ --collect-only
+```
+
+**Adding a New Plugin**:
+1. Create plugin directory: `plugins/my_plugin/`
+2. Add `__init__.py` with `PLUGIN_MANIFEST`, `MODEL_REQUIREMENTS`, `create_engine`
+3. Run `pytest tests/plugins/` — tests automatically discover and test your plugin!
+
+**When to Add Plugin-Specific Tests**:
+Auto-discovery tests cover generic contract validation. Create plugin-specific tests in `tests/test_<plugin>_plugin.py` for:
+- Integration with real dependencies (e.g., KPipeline for Kokoro)
+- Specific voice IDs and behavior
+- Plugin-specific parameters and features
+
+---
+
+### 1. Contract Tests (`tests/contracts/`)
+
+**Purpose**: Verify that every plugin satisfies the architectural contract. These tests ensure the Plugin Architecture's invariants are maintained.
+
+**What They Guarantee**:
+- Every plugin exports `PLUGIN_MANIFEST`, `MODEL_REQUIREMENTS`, `create_engine`
+- `create_engine` is atomic (succeeds fully or raises and cleans up)
+- `Engine.createSession()` returns valid `EngineSession`, transfers ownership
+- `Engine.dispose()` is idempotent, never raises
+- After `dispose()`, all methods raise `EngineError`
+- `EngineSession.synthesize()` returns `SynthesizedAudio` or raises `EngineError` (session remains usable)
+- `EngineSession.dispose()` is idempotent, never raises
+- Capability interfaces (`VoiceLister`, `PreviewGenerator`, etc.) are correctly implemented
+- Plugin Loader discovers, validates, and loads plugins correctly
+- Plugin Manager creates, caches, and disposes engines correctly
+- Value objects are immutable and have correct equality semantics
+- Error hierarchy is preserved (`EngineError` base with subtypes)
+
+**Why They Exist**:
+- Provide **compile-time-like guarantees** for a dynamic plugin system
+- Enable **safe plugin ecosystem** — host can trust any loaded plugin
+- Catch **architectural violations** early (missing dispose, wrong return types, etc.)
+- Document the **contract** in executable form
+
+**What Every New Plugin Must Pass**:
+```bash
+pytest tests/contracts/ -v
+# All tests must pass
+```
+
+**Running Contract Tests**:
+```bash
+# All contract tests
+pytest tests/contracts/
+
+# Specific contract
+pytest tests/contracts/test_engine_contract.py
+
+# With coverage
+pytest tests/contracts/ --cov=abogen.tts_plugin
+```
+
+---
+
+### 2. Behavioral Tests (`tests/test_behavioral_regression.py`)
+
+**Purpose**: Verify external user-facing behavior using only public API. These tests are **not coupled to internal implementation**.
+
+**What They Test**:
+- Synthesis with various inputs (short, long, empty, unicode, mixed scripts)
+- Voice selection and listing
+- Parameter handling (speed, etc.)
+- Error scenarios (unknown plugin, disposal, etc.)
+- Resource cleanup (dispose idempotency, no leaks)
+- Pipeline utility (`create_pipeline`)
+
+**Why They Test Public Behavior Only**:
+- **Refactoring safety**: Internal changes don't break tests
+- **Real-world usage**: Tests match how consumers actually use the API
+- **Plugin agnostic**: Parametrized across Kokoro, SuperTonic, and mock plugins
+- **Regression detection**: Catch behavioral regressions regardless of implementation
+
+**What They Don't Test**:
+- Internal class structure
+- Private methods
+- Implementation details (how audio is generated, model loading internals)
+
+**Running Behavioral Tests**:
+```bash
+# All behavioral tests
+pytest tests/test_behavioral_regression.py -v
+
+# With specific plugin (if installed)
+pytest tests/test_behavioral_regression.py -v -k "kokoro"
+```
+
+---
+
+### 4. Unit Tests (`tests/`)
+
+**Purpose**: Test individual modules in isolation.
+
+**Examples**:
+- `test_book_parser.py` — EPUB/PDF/text parsing
+- `test_text_normalization.py` — Text preprocessing
+- `test_chunk_helpers.py` — Text chunking logic
+- `test_voice_cache.py` — Voice caching
+
+---
+
+### 5. Integration Tests
+
+**Purpose**: Test cross-component interactions.
+
+**Examples**:
+- `test_kokoro_plugin.py` — Full Kokoro plugin integration
+- `test_supertonic_plugin.py` — Full SuperTonic plugin integration
+- `test_conversion_series.py` — End-to-end conversion pipeline
+
+---
+
+## Test Architecture
+
+```
+tests/
+├── contracts/           # Contract tests (architectural compliance)
+│   ├── conftest.py      # Shared fixtures (FakeEngine, FakeSession)
+│   ├── test_manifest_contract.py
+│   ├── test_plugin_contract.py
+│   ├── test_engine_contract.py
+│   ├── test_session_contract.py
+│   ├── test_capabilities_contract.py
+│   ├── test_loader_contract.py
+│   ├── test_plugin_manager_contract.py
+│   ├── test_types_contract.py
+│   ├── test_errors_contract.py
+│   ├── test_host_context_contract.py
+│   └── test_integration.py
+├── test_behavioral_regression.py  # Behavioral tests (public API)
+├── test_kokoro_plugin.py          # Kokoro integration
+├── test_supertonic_plugin.py      # SuperTonic integration
+└── ...                            # Other unit/integration tests
+```
+
+---
+
+## Adding Tests for a New Plugin
+
+### Auto-Discovery Tests (Automatic!)
+
+**No manual test creation required!** When you add a new plugin to `plugins/`:
+
+1. Create plugin directory: `plugins/my_plugin/`
+2. Add `__init__.py` with required exports:
+   ```python
+   PLUGIN_MANIFEST = PluginManifest(...)
+   MODEL_REQUIREMENTS = [...]
+   def create_engine(...): ...
+   ```
+3. Run `pytest tests/plugins/` — auto-discovery tests automatically find and test your plugin!
+
+**What's Tested Automatically**:
+- Manifest structure and required fields
+- API version compatibility
+- Engine creation and dispose contract
+- Capability implementation (if declared)
+
+### Plugin-Specific Tests (Optional)
+
+Create `tests/test_my_plugin_plugin.py` for:
+- Integration with real backend (e.g., KPipeline for Kokoro)
+- Specific voice IDs and behavior
+- Plugin-specific parameters and features
+
+### Contract Tests (Deprecated for New Plugins)
+
+**Note**: Auto-discovery tests (`tests/plugins/`) now cover contract validation for all plugins. Manual contract tests in `tests/contracts/` are only needed for testing internal architecture components.
+
+### Behavioral Tests (Recommended)
+
+Add parametrized tests to `tests/test_behavioral_regression.py`:
+
+```python
+# In _plugin_ids list, add your plugin
+_plugin_ids = ["kokoro", "supertonic", "my_plugin"]
+_plugin_engines["my_plugin"] = _YourMockEngine
+_plugin_default_voices["my_plugin"] = "voice1"
+_plugin_all_voices["my_plugin"] = ["voice1", "voice2"]
+```
+
+All existing behavioral tests will automatically run against your plugin.
+
+---
+
+## Continuous Integration
+
+```yaml
+# .github/workflows/test.yml
+- name: Contract Tests
+  run: pytest tests/contracts/ -v
+
+- name: Behavioral Tests
+  run: pytest tests/test_behavioral_regression.py -v
+
+- name: Unit & Integration Tests
+  run: pytest tests/ -v --ignore=tests/test_behavioral_regression.py
+```
+
+---
+
+## Test Design Principles
+
+### Contract Tests
+- **No mocks** for the system under test (test real plugin loading)
+- **Strict assertions** on types and behavior
+- **Document architecture** in test names and docstrings
+- **Fail fast** on architectural violations
+
+### Behavioral Tests
+- **Only public API** (`create_pipeline`, `Engine`, `EngineSession`, `PluginManager`)
+- **Parametrized** across plugins
+- **Realistic scenarios** (long text, unicode, mixed scripts)
+- **No implementation coupling** (test behavior, not internals)
+
+### General
+- **Fast**: Unit tests < 1s, Contract tests < 5s, Behavioral < 30s
+- **Isolated**: No shared state between tests
+- **Deterministic**: Same input → same output
+- **Descriptive names**: `test_<component>_<scenario>_<expected>`

docs/tts-plugin-architecture.md

@@ -0,0 +1,689 @@
+# TTS Plugin Architecture — Final Specification
+
+## 1. Core Domain
+
+Zero dependencies. Pure business logic.
+
+### 1.1 Engine
+
+Factory for sessions. Stateless. Thread-safe for createSession().
+
+```
+interface Engine:
+  createSession() -> EngineSession
+  dispose() -> void
+```
+
+**createSession() contract**:
+- Returns: EngineSession
+- Raises: EngineError on failure
+- Ownership: Transfers to caller
+- Thread-safe: Yes
+
+**dispose() contract**:
+- Releases engine resources
+- Caller must ensure all sessions created by this engine are disposed before calling dispose()
+- Disposing an engine while any session is still alive violates the API contract; behavior is undefined
+- Idempotent: Safe to call multiple times
+- Never raises: Catches and logs internally
+- After dispose(): All methods except dispose() raise EngineError
+
+### 1.2 EngineSession
+
+Owns mutable execution state isolated from other concurrent work. NOT thread-safe.
+
+```
+interface EngineSession:
+  synthesize(request: SynthesisRequest) -> SynthesizedAudio
+  dispose() -> void
+```
+
+**synthesize() contract**:
+- Returns: SynthesizedAudio
+- Raises: EngineError on failure (session remains usable)
+- Thread-safe: No
+
+**dispose() contract**:
+- Releases session resources
+- Idempotent: Safe to call multiple times
+- Never raises: Catches and logs internally
+- After dispose(): All methods except dispose() raise EngineError
+
+### 1.3 SynthesisRequest
+
+Immutable value object.
+
+```
+SynthesisRequest:
+  text: string
+  voice: VoiceSelection
+  parameters: ParameterValues
+  format: AudioFormat
+```
+
+### 1.4 SynthesizedAudio
+
+Immutable value object.
+
+```
+SynthesizedAudio:
+  data: bytes
+  format: AudioFormat
+  duration: Duration
+```
+
+### 1.5 VoiceSelection
+
+Immutable value object. Opaque to engine.
+
+```
+VoiceSelection:
+  source: string
+  key: string
+  payload: any = None  # Optional; required for clone/blend sources
+```
+
+### 1.6 ParameterValues
+
+Immutable value object. Behaves like Mapping[str, Any].
+
+```
+ParameterValues:
+  values: Mapping[str, Any]
+```
+
+### 1.7 AudioFormat
+
+Immutable value object.
+
+```
+AudioFormat:
+  mime: string
+  extension: string
+```
+
+### 1.8 Duration
+
+Immutable value object.
+
+```
+Duration:
+  seconds: number
+```
+
+### 1.9 EngineConfig
+
+Engine initialization settings only. No resource references.
+
+```
+EngineConfig:
+  device: string    # "cpu", "cuda:0", etc.
+  # Engine-specific settings (if any)
+  # Unknown keys are ignored (no error)
+```
+
+---
+
+## 2. Error Hierarchy
+
+Typed exceptions. Engines raise EngineError or subtypes. Never raw exceptions.
+
+```
+EngineError (base)
+├── ModelNotFoundError
+├── ModelLoadError
+├── NetworkError
+├── InvalidInputError
+├── ConfigurationError
+├── CancelledError
+└── InternalError
+```
+
+**Contract**:
+- synthesize() raises EngineError on failure, session remains usable
+- dispose() never raises (catches and logs internally)
+- create_engine() raises EngineError on failure, cleans up partially created resources
+- createSession() raises EngineError on failure, no partially initialized session returned
+- cancel() causes synthesize() to raise CancelledError
+
+---
+
+## 3. Capability Interfaces (Optional)
+
+Engines implement only what they support. Capabilities are additive.
+
+### 3.1 VoiceLister
+
+```
+interface VoiceLister:
+  listVoices(sourceId: string) -> list[VoiceManifest]
+```
+
+### 3.2 PreviewGenerator
+
+```
+interface PreviewGenerator:
+  generatePreview(voice: VoiceSelection, text: string) -> SynthesizedAudio
+```
+
+### 3.3 ModelRequirements
+
+Static at plugin level, not engine level. Host reads before creating engine.
+
+```
+MODEL_REQUIREMENTS = list[ModelManifest]
+```
+
+### 3.4 StreamingSynthesizer
+
+Optional capability of EngineSession, not Engine.
+
+```
+interface StreamingSynthesizer:
+  synthesizeStream(request: SynthesisRequest) -> Iterator[bytes]
+```
+
+**Iterator contract**:
+- Yields audio chunks as they become available
+- Raises CancelledError if cancel() is called during iteration
+- Raises EngineError on synthesis failure
+- Iterator exhaustion = synthesis complete
+- Session remains usable after iterator completes
+
+### 3.5 CancelableSession
+
+Optional capability for engines that support cancellation.
+
+```
+interface CancelableSession:
+  cancel() -> void
+```
+
+**cancel() contract**:
+- Cancels in-progress synthesize()
+- synthesize() raises CancelledError (subtype of EngineError)
+- EngineSession remains usable after cancellation (unless implementation documents otherwise)
+
+---
+
+## 4. Plugin Manifest
+
+Static metadata. Immutable. No dependencies.
+
+### 4.1 PluginManifest
+
+```
+PluginManifest:
+  id: string
+  name: string
+  version: string
+  api_version: string  # semver format: MAJOR.MINOR
+  description: string
+  author: string
+  capabilities: list[string]
+  requires: RequirementManifest
+  engine: EngineManifest
+```
+
+**api_version contract**:
+- Format: semver (MAJOR.MINOR)
+- Compatibility: Host rejects plugin if major version differs
+- Minor version: backward compatible, Host accepts higher minor
+
+### 4.2 EngineManifest
+
+```
+EngineManifest:
+  voiceSources: list[VoiceSourceManifest]
+  parameters: list[ParameterManifest]
+  audioFormats: list[AudioFormatManifest]
+```
+
+### 4.3 VoiceSourceManifest
+
+```
+VoiceSourceManifest:
+  id: string
+  name: string
+  type: string    # "list", "speaker_id", "clone", "blend", "generate", "none"
+  config: any
+```
+
+### 4.4 VoiceManifest
+
+```
+VoiceManifest:
+  id: string
+  name: string
+  tags: list[string]
+```
+
+### 4.5 ParameterManifest
+
+```
+ParameterManifest:
+  id: string
+  name: string
+  description: string
+  type: string    # "float", "int", "string", "boolean", "enum"
+  default: any
+  min: number (optional)
+  max: number (optional)
+  step: number (optional)
+  options: list[EnumOption] (optional)
+  unit: string (optional)
+  group: string (optional)
+```
+
+### 4.6 AudioFormatManifest
+
+```
+AudioFormatManifest:
+  mime: string
+  extension: string
+```
+
+### 4.7 EnumOption
+
+```
+EnumOption:
+  value: string
+  label: string
+```
+
+### 4.8 RequirementManifest
+
+```
+RequirementManifest:
+  gpu: GpuRequirement (optional)
+  memory: number (optional)
+  internet: boolean (optional)
+```
+
+### 4.9 GpuRequirement
+
+```
+GpuRequirement:
+  required: boolean
+  type: string (optional)
+  memory: number (optional)
+```
+
+### 4.10 ModelManifest
+
+```
+ModelManifest:
+  id: string
+  name: string
+  size: string
+```
+
+---
+
+## 5. Host Services
+
+### 5.1 HostContext
+
+Minimal. 3 fields maximum. No business logic.
+
+```
+HostContext:
+  config_dir: Path      # For API keys, preferences
+  logger: Logger        # For logging
+  http_client: HttpClient  # For network requests
+```
+
+---
+
+## 6. Plugin Contract
+
+### 6.1 Plugin Exports
+
+```python
+# plugins/kokoro/__init__.py
+
+PLUGIN_MANIFEST = PluginManifest(...)
+MODEL_REQUIREMENTS = [...]  # Static at plugin level
+
+def create_engine(
+  context: HostContext,
+  model_path: Path | None,
+  config: EngineConfig
+) -> Engine:
+  """Create engine. Atomic: succeeds fully or raises and cleans up."""
+  ...
+```
+
+### 6.2 create_engine() Contract
+
+- Parameters:
+  - context: HostContext (host services)
+  - model_path: Path | None (resolved model path, or None for cloud/no-model engines)
+  - config: EngineConfig (engine initialization settings)
+- Returns: Engine
+- Raises: EngineError on failure
+- Atomic: Succeeds fully or cleans up and raises
+- Thread-safe: Can be called from any thread
+
+---
+
+## 7. Object Lifecycle
+
+### 7.1 Engine Lifecycle
+
+```
+1. DISCOVERY
+   Host scans plugin directories
+   Loads PLUGIN_MANIFEST and MODEL_REQUIREMENTS
+
+2. MODEL DOWNLOAD (if MODEL_REQUIREMENTS non-empty)
+   Host reads MODEL_REQUIREMENTS
+   Downloads/caches required models
+   Resolves model_path for create_engine()
+
+3. ACTIVATION
+   Host calls create_engine(context, model_path, config)
+   Engine created, ready to use
+   Raises EngineError on failure
+
+4. SESSION CREATION
+   Client calls engine.createSession()
+   Returns EngineSession
+   Ownership transfers to caller
+   Raises EngineError on failure
+   No partially initialized session returned
+
+5. SYNTHESIS
+   Client calls session.synthesize(request)
+   Returns SynthesizedAudio
+   Raises EngineError on failure (session remains usable)
+
+6. SESSION DISPOSAL
+   Client calls session.dispose()
+   Releases session resources
+
+7. DEACTIVATION
+   Client calls engine.dispose()
+   Caller must ensure all sessions are disposed first
+   Disposing engine while sessions are alive is undefined behavior
+   Releases engine resources
+```
+
+### 7.2 EngineSession Lifecycle
+
+```
+1. CREATION
+   Created by Engine.createSession()
+   Ownership transfers to caller
+   Raises EngineError on failure
+
+2. USAGE
+   Client calls synthesize() one or more times
+   Each call returns SynthesizedAudio or raises EngineError
+   Session remains usable after synthesize() failure
+   If CancelableSession: cancel() causes synthesize() to raise CancelledError
+   If StreamingSynthesizer: iterator raises CancelledError on cancel(), EngineError on failure
+
+3. DISPOSAL
+   Client calls dispose()
+   Releases session resources
+   After dispose(), all methods except dispose() raise EngineError
+```
+
+### 7.3 Ownership Rules
+
+- Engine.createSession() transfers ownership of the returned session to the caller
+- Caller is responsible for disposing all sessions before disposing the engine
+- Engine does not track sessions; it has no lifecycle registry
+- Disposing an engine while any session is still alive violates the API contract; behavior is undefined
+- This design avoids coupling, synchronization overhead, and lifecycle registry complexity
+
+### 7.4 Concurrent Operations
+
+**Engine.dispose() concurrent with Engine.createSession()**:
+- createSession() must either succeed with fully initialized EngineSession or raise EngineError
+- Partially initialized EngineSession must never be returned
+- After dispose() completes, subsequent createSession() calls must raise EngineError
+
+**EngineSession.dispose() concurrent with EngineSession.synthesize()**:
+- Not thread-safe. Caller must ensure synthesize() completes before dispose().
+
+**EngineSession.dispose() concurrent with StreamingSynthesizer.synthesizeStream()**:
+- Not thread-safe. Caller must ensure stream iteration completes before dispose().
+
+---
+
+## 8. Thread Safety Contract
+
+| Component | Thread-safe | Notes |
+|-----------|-------------|-------|
+| Engine | Yes | createSession() can be called from any thread |
+| EngineSession | No | synthesize() must be called from one thread at a time |
+| HostContext | Yes | Provides shared services |
+| VoiceSelection | Yes | Immutable value object |
+| ParameterValues | Yes | Immutable value object |
+| AudioFormat | Yes | Immutable value object |
+| EngineConfig | Yes | Immutable value object |
+
+---
+
+## 9. dispose() Contract
+
+**General rules**:
+- Calling dispose() multiple times is safe (no-op on second call)
+- dispose() never raises exceptions (catches and logs internally)
+- After dispose(), all methods except dispose() raise EngineError
+
+**Engine.dispose()**:
+- Caller must ensure all sessions are disposed first
+- Disposing engine while sessions are alive violates API contract; behavior is undefined
+- Releases engine resources
+
+**EngineSession.dispose()**:
+- Releases session resources
+
+---
+
+## 10. Dependency Rules
+
+```
+Core Domain (Engine, EngineSession, Value Objects)
+  -> No dependencies
+
+Plugin Manifest (PluginManifest, ModelManifest, etc.)
+  -> No dependencies
+
+Host Context (HostContext)
+  -> Depends on: Core Domain (for types)
+
+Plugin Implementation
+  -> Depends on: Core Domain, Host Context
+
+Host
+  -> Depends on: Core Domain, Plugin Manifest
+```
+
+**Forbidden**:
+- Core Domain -> anything else
+- Plugin Manifest -> anything else
+- Plugin Implementation -> Host (only receives HostContext)
+- Host -> Plugin Implementation (only via create_engine function)
+
+---
+
+## 11. Architectural Invariants
+
+1. Core Domain has zero dependencies
+2. Plugins receive HostContext at creation, not via global state
+3. Model requirements are static (plugin level), not dynamic (engine level)
+4. Host validates capability implementation at load time: each capability declared in PluginManifest.capabilities must be implemented by the exported object via the corresponding interface
+5. synthesize() raises typed exceptions, not returns Result
+6. dispose() is idempotent and never raises
+7. No global state, no service locator
+8. VoiceSelection and ParameterValues are opaque to engine
+9. Display information comes from VoiceManifest
+10. HostContext is minimal (3 fields max)
+11. EngineConfig contains only engine settings, not resource references
+12. EngineSession owns mutable execution state isolated from other concurrent work
+13. Engine.createSession() transfers ownership to caller
+14. Caller must dispose all sessions before disposing engine
+15. After dispose(), all methods except dispose() raise EngineError
+16. create_engine() is atomic (all-or-nothing)
+17. Garbage collection without dispose() may leak (documented)
+18. Capabilities are additive (new capabilities don't break old plugins)
+19. api_version enables compatibility checking
+20. createSession() returns fully initialized session or raises, never partial
+21. cancel() causes synthesize() to raise CancelledError
+22. EngineSession remains usable after cancellation
+23. Engine does not track sessions; no lifecycle registry
+
+---
+
+## 12. Validation Examples
+
+### 12.1 Kokoro
+
+```python
+PLUGIN_MANIFEST = PluginManifest(
+  id="kokoro",
+  api_version="1.0",
+  capabilities=["voice_list", "preview", "voice_blend"],
+  engine=EngineManifest(
+    voiceSources=[
+      VoiceSourceManifest(id="builtin", type="list", config={"voices": [...]}),
+      VoiceSourceManifest(id="formula", type="blend", config={"syntax": "{a}*0.5+{b}*0.5"}),
+    ],
+    parameters=[ParameterManifest(id="speed", type="float", default=1.0, min=0.5, max=2.0)],
+    audioFormats=[AudioFormatManifest(mime="audio/wav", extension="wav")],
+  ),
+)
+
+MODEL_REQUIREMENTS = []
+
+def create_engine(context: HostContext, model_path: Path | None, config: EngineConfig) -> Engine:
+  model = load_kokoro(model_path)
+  return KokoroEngine(model, config.device)
+```
+
+### 12.2 SuperTonic
+
+```python
+PLUGIN_MANIFEST = PluginManifest(
+  id="supertonic",
+  api_version="1.0",
+  capabilities=["voice_list", "preview"],
+  engine=EngineManifest(
+    voiceSources=[VoiceSourceManifest(id="builtin", type="list", config={"voices": [...]})],
+    parameters=[
+      ParameterManifest(id="speed", type="float", default=1.0, min=0.5, max=2.0),
+      ParameterManifest(id="steps", type="int", default=20, min=5, max=50),
+    ],
+    audioFormats=[AudioFormatManifest(mime="audio/wav", extension="wav")],
+  ),
+)
+
+MODEL_REQUIREMENTS = []
+
+def create_engine(context: HostContext, model_path: Path | None, config: EngineConfig) -> Engine:
+  model = load_supertonic(model_path)
+  return SuperTonicEngine(model, config.device)
+```
+
+### 12.3 ElevenLabs
+
+```python
+PLUGIN_MANIFEST = PluginManifest(
+  id="elevenlabs",
+  api_version="1.0",
+  capabilities=["voice_list"],
+  requires=RequirementManifest(internet=True),
+  engine=EngineManifest(
+    voiceSources=[VoiceSourceManifest(id="cloud", type="list", config={"speakers": [...]})],
+    parameters=[ParameterManifest(id="stability", type="float", default=0.5, min=0.0, max=1.0)],
+    audioFormats=[AudioFormatManifest(mime="audio/mpeg", extension="mp3")],
+  ),
+)
+
+MODEL_REQUIREMENTS = []
+
+def create_engine(context: HostContext, model_path: Path | None, config: EngineConfig) -> Engine:
+  api_key = (context.config_dir / "elevenlabs_key").read_text()
+  return ElevenLabsEngine(api_key)
+```
+
+### 12.4 Piper
+
+```python
+PLUGIN_MANIFEST = PluginManifest(
+  id="piper",
+  api_version="1.0",
+  capabilities=[],
+  engine=EngineManifest(
+    voiceSources=[VoiceSourceManifest(id="downloadable", type="list", config={"models": [...]})],
+    parameters=[ParameterManifest(id="speed", type="float", default=1.0, min=0.5, max=2.0)],
+    audioFormats=[AudioFormatManifest(mime="audio/wav", extension="wav")],
+  ),
+)
+
+MODEL_REQUIREMENTS = [
+  ModelManifest(id="en_US-lessac-medium", name="English Lessac Medium", size="100MB"),
+]
+
+def create_engine(context: HostContext, model_path: Path | None, config: EngineConfig) -> Engine:
+  return PiperEngine(model_path, config.device)
+```
+
+### 12.5 XTTS (with streaming and cancellation)
+
+```python
+PLUGIN_MANIFEST = PluginManifest(
+  id="xtts",
+  api_version="1.0",
+  capabilities=["voice_list", "preview", "voice_clone", "streaming", "cancel"],
+  requires=RequirementManifest(gpu=GpuRequirement(required=True, type="cuda")),
+  engine=EngineManifest(
+    voiceSources=[
+      VoiceSourceManifest(id="speakers", type="speaker_id", config={"speakers": [...]}),
+      VoiceSourceManifest(id="clone", type="clone", config={"requiresAudio": True, "maxDuration": 30}),
+    ],
+    parameters=[ParameterManifest(id="temperature", type="float", default=0.7, min=0.1, max=1.0)],
+    audioFormats=[AudioFormatManifest(mime="audio/wav", extension="wav")],
+  ),
+)
+
+MODEL_REQUIREMENTS = [
+  ModelManifest(id="xtts_v2", name="XTTS v2", size="2GB"),
+]
+
+def create_engine(context: HostContext, model_path: Path | None, config: EngineConfig) -> Engine:
+  return XTTSEngine(model_path, config.device)
+```
+
+XTTS session implements: EngineSession, StreamingSynthesizer, CancelableSession.
+
+---
+
+## 13. Summary of All Decisions
+
+| Aspect | Decision |
+|--------|----------|
+| Engine | Factory, stateless, thread-safe for createSession() |
+| EngineSession | Owns mutable execution state, not thread-safe |
+| EngineSession ownership | Caller owns (transferred from createSession) |
+| Engine session tracking | None; engine does not track sessions |
+| StreamingSynthesizer | Optional capability of EngineSession |
+| CancelableSession | Optional capability, cancel() raises CancelledError |
+| dispose() | Idempotent, never raises |
+| Engine.dispose() | Caller must dispose sessions first; undefined if violated |
+| createSession() | Raises EngineError on failure, no partial sessions |
+| create_engine() | Atomic, takes context, model_path, config |
+| EngineConfig | Engine settings only, no resource references |
+| model_path | Separate argument, not in EngineConfig |
+| MODEL_REQUIREMENTS | Static at plugin level |
+| HostContext | Minimal (3 fields) |
+| Error handling | Typed exceptions (EngineError hierarchy) |
+| Thread safety | Documented per component |
+| Capabilities | Additive, optional interfaces |
+| API versioning | api_version in manifest |
+| Concurrent dispose/createSession | Fully initialized session or EngineError |
+| Concurrent dispose/synthesizeStream | Not thread-safe; caller must complete iteration first |

plugins/kokoro/__init__.py

@@ -0,0 +1,185 @@
+"""Kokoro TTS Plugin for the TTS Plugin Architecture.
+
+This plugin provides a Kokoro-based TTS engine that implements the
+Plugin API contract. It wraps the existing Kokoro backend in the
+new Engine/EngineSession architecture.
+
+Exports:
+    - PLUGIN_MANIFEST: PluginManifest
+    - MODEL_REQUIREMENTS: list[ModelManifest]
+    - create_engine: Factory function
+"""
+
+from __future__ import annotations
+
+from pathlib import Path
+from typing import Any
+
+from abogen.tts_plugin.engine import Engine
+from abogen.tts_plugin.host_context import HostContext
+from abogen.tts_plugin.manifest import (
+    AudioFormatManifest,
+    EngineManifest,
+    ModelManifest,
+    ParameterManifest,
+    PluginManifest,
+    RequirementManifest,
+    VoiceManifest,
+    VoiceSourceManifest,
+)
+from abogen.tts_plugin.types import EngineConfig
+
+from .engine import KokoroEngine
+
+
+def _load_kpipeline() -> Any:
+    """Lazy-load Kokoro dependencies."""
+    # Transformers 5.x moved AlbertModel out of top-level imports.
+    # Monkey-patch before kokoro imports it.
+    import transformers
+    if not hasattr(transformers, "AlbertModel"):
+        from transformers.models.albert import AlbertModel as _AlbertModel
+        transformers.AlbertModel = _AlbertModel
+
+    from kokoro import KPipeline  # type: ignore[import-not-found]
+    return KPipeline
+
+
+PLUGIN_MANIFEST = PluginManifest(
+    id="kokoro",
+    name="Kokoro",
+    version="0.9.4",
+    api_version="1.0",
+    description="Kokoro TTS engine - high quality multilingual text-to-speech",
+    author="Kokoro Team",
+    capabilities=("voice_list",),
+    requires=RequirementManifest(
+        internet=False,
+    ),
+    engine=EngineManifest(
+        voiceSources=(
+            VoiceSourceManifest(
+                id="builtin",
+                name="Built-in Voices",
+                type="list",
+                config={"voices": "See listVoices()"},
+            ),
+        ),
+        parameters=(
+            ParameterManifest(
+                id="speed",
+                name="Speed",
+                description="Speech speed multiplier",
+                type="float",
+                default=1.0,
+                min=0.5,
+                max=2.0,
+                step=0.1,
+            ),
+        ),
+        audioFormats=(
+            AudioFormatManifest(mime="audio/wav", extension="wav"),
+        ),
+    ),
+    voices=(
+        VoiceManifest(id="af_alloy", name="Alloy", tags=("en", "female")),
+        VoiceManifest(id="af_aoede", name="Aoede", tags=("en", "female")),
+        VoiceManifest(id="af_bella", name="Bella", tags=("en", "female")),
+        VoiceManifest(id="af_heart", name="Heart", tags=("en", "female")),
+        VoiceManifest(id="af_jessica", name="Jessica", tags=("en", "female")),
+        VoiceManifest(id="af_kore", name="Kore", tags=("en", "female")),
+        VoiceManifest(id="af_nicole", name="Nicole", tags=("en", "female")),
+        VoiceManifest(id="af_nova", name="Nova", tags=("en", "female")),
+        VoiceManifest(id="af_river", name="River", tags=("en", "female")),
+        VoiceManifest(id="af_sarah", name="Sarah", tags=("en", "female")),
+        VoiceManifest(id="af_sky", name="Sky", tags=("en", "female")),
+        VoiceManifest(id="am_adam", name="Adam", tags=("en", "male")),
+        VoiceManifest(id="am_echo", name="Echo", tags=("en", "male")),
+        VoiceManifest(id="am_eric", name="Eric", tags=("en", "male")),
+        VoiceManifest(id="am_fenrir", name="Fenrir", tags=("en", "male")),
+        VoiceManifest(id="am_liam", name="Liam", tags=("en", "male")),
+        VoiceManifest(id="am_michael", name="Michael", tags=("en", "male")),
+        VoiceManifest(id="am_onyx", name="Onyx", tags=("en", "male")),
+        VoiceManifest(id="am_puck", name="Puck", tags=("en", "male")),
+        VoiceManifest(id="am_santa", name="Santa", tags=("en", "male")),
+        VoiceManifest(id="bf_alice", name="Alice", tags=("en", "female")),
+        VoiceManifest(id="bf_emma", name="Emma", tags=("en", "female")),
+        VoiceManifest(id="bf_isabella", name="Isabella", tags=("en", "female")),
+        VoiceManifest(id="bf_lily", name="Lily", tags=("en", "female")),
+        VoiceManifest(id="bm_daniel", name="Daniel", tags=("en", "male")),
+        VoiceManifest(id="bm_fable", name="Fable", tags=("en", "male")),
+        VoiceManifest(id="bm_george", name="George", tags=("en", "male")),
+        VoiceManifest(id="bm_lewis", name="Lewis", tags=("en", "male")),
+        VoiceManifest(id="ef_dora", name="Dora", tags=("es", "female")),
+        VoiceManifest(id="em_alex", name="Alex", tags=("es", "male")),
+        VoiceManifest(id="em_santa", name="Santa", tags=("es", "male")),
+        VoiceManifest(id="ff_siwis", name="Siwis", tags=("fr", "female")),
+        VoiceManifest(id="hf_alpha", name="Alpha", tags=("hi", "female")),
+        VoiceManifest(id="hf_beta", name="Beta", tags=("hi", "female")),
+        VoiceManifest(id="hm_omega", name="Omega", tags=("hi", "male")),
+        VoiceManifest(id="hm_psi", name="Psi", tags=("hi", "male")),
+        VoiceManifest(id="if_sara", name="Sara", tags=("it", "female")),
+        VoiceManifest(id="im_nicola", name="Nicola", tags=("it", "male")),
+        VoiceManifest(id="jf_alpha", name="Alpha", tags=("ja", "female")),
+        VoiceManifest(id="jf_gongitsune", name="Gongitsune", tags=("ja", "female")),
+        VoiceManifest(id="jf_nezumi", name="Nezumi", tags=("ja", "female")),
+        VoiceManifest(id="jf_tebukuro", name="Tebukuro", tags=("ja", "female")),
+        VoiceManifest(id="jm_kumo", name="Kumo", tags=("ja", "male")),
+        VoiceManifest(id="pf_dora", name="Dora", tags=("pt", "female")),
+        VoiceManifest(id="pm_alex", name="Alex", tags=("pt", "male")),
+        VoiceManifest(id="pm_santa", name="Santa", tags=("pt", "male")),
+        VoiceManifest(id="zf_xiaobei", name="Xiaobei", tags=("zh", "female")),
+        VoiceManifest(id="zf_xiaoni", name="Xiaoni", tags=("zh", "female")),
+        VoiceManifest(id="zf_xiaoxiao", name="Xiaoxiao", tags=("zh", "female")),
+        VoiceManifest(id="zf_xiaoyi", name="Xiaoyi", tags=("zh", "female")),
+        VoiceManifest(id="zm_yunjian", name="Yunjian", tags=("zh", "male")),
+        VoiceManifest(id="zm_yunxi", name="Yunxi", tags=("zh", "male")),
+        VoiceManifest(id="zm_yunxia", name="Yunxia", tags=("zh", "female")),
+        VoiceManifest(id="zm_yunyang", name="Yunyang", tags=("zh", "male")),
+    ),
+)
+
+MODEL_REQUIREMENTS: list[ModelManifest] = []
+
+
+def create_engine(
+    context: HostContext,
+    model_path: Path | None,
+    config: EngineConfig,
+) -> Engine:
+    """Create a Kokoro engine instance.
+
+    This function is the plugin entry point. It must be atomic:
+    succeed fully or raise EngineError and clean up.
+
+    Args:
+        context: Host services (config dir, logger, http client).
+        model_path: Resolved model path, or None for default.
+        config: Engine initialization settings (device, etc.).
+
+    Returns:
+        A fully initialized KokoroEngine instance.
+
+    Raises:
+        EngineError: On failure. Cleans up partially created resources.
+    """
+    try:
+        KPipeline = _load_kpipeline()
+
+        # Determine repo_id from model_path or use default
+        repo_id = "hexgrad/Kokoro-82M"
+        if model_path is not None:
+            # If a specific model path is provided, use it as repo_id
+            repo_id = str(model_path)
+
+        pipeline = KPipeline(
+            lang_code=config.lang_code,
+            repo_id=repo_id,
+            device=config.device,
+        )
+
+        engine = KokoroEngine(pipeline)
+        return engine
+    except Exception as e:
+        from abogen.tts_plugin.errors import EngineError as EngineErrorClass
+        raise EngineErrorClass(f"Failed to create Kokoro engine: {e}") from e

plugins/kokoro/engine.py

@@ -0,0 +1,118 @@
+"""Kokoro Engine adapter for the TTS Plugin Architecture.
+
+This module adapts the existing Kokoro backend to the new Engine/EngineSession
+protocol. It wraps the KokoroBackend without modifying it.
+"""
+
+from __future__ import annotations
+
+import logging
+from typing import Any
+
+import numpy as np
+
+from abogen.tts_plugin.capabilities import VoiceLister
+from abogen.tts_plugin.engine import Engine, EngineSession
+from abogen.tts_plugin.errors import EngineError
+from abogen.tts_plugin.manifest import VoiceManifest
+from abogen.tts_plugin.types import (
+    AudioFormat,
+    Duration,
+    SynthesisRequest,
+    SynthesizedAudio,
+)
+
+logger = logging.getLogger(__name__)
+
+# Sample rate for Kokoro audio
+_KOKORO_SAMPLE_RATE = 24000
+
+
+class KokoroSession:
+    """EngineSession implementation for Kokoro.
+
+    Owns mutable execution state for synthesis.
+    NOT thread-safe.
+    """
+
+    def __init__(self, pipeline: Any) -> None:
+        self._pipeline = pipeline
+        self._disposed = False
+
+    def synthesize(self, request: SynthesisRequest) -> SynthesizedAudio:
+        """Synthesize audio from text using Kokoro."""
+        if self._disposed:
+            raise EngineError("Session disposed")
+
+        try:
+            voice = request.voice.key
+            speed = request.parameters.values.get("speed", 1.0)
+            split_pattern = request.parameters.values.get("split_pattern", None)
+
+            audio_parts: list[np.ndarray] = []
+            for segment in self._pipeline(
+                request.text,
+                voice=voice,
+                speed=speed,
+                split_pattern=split_pattern,
+            ):
+                audio = segment.audio
+                if hasattr(audio, "numpy"):
+                    audio = audio.numpy()
+                audio_parts.append(np.asarray(audio, dtype="float32"))
+
+            if not audio_parts:
+                return SynthesizedAudio(
+                    data=b"",
+                    format=AudioFormat(mime="audio/wav", extension="wav"),
+                    duration=Duration(seconds=0.0),
+                )
+
+            combined = np.concatenate(audio_parts).astype("float32", copy=False)
+            audio_bytes = combined.tobytes()
+            duration_seconds = len(combined) / _KOKORO_SAMPLE_RATE
+
+            return SynthesizedAudio(
+                data=audio_bytes,
+                format=AudioFormat(mime="audio/wav", extension="wav"),
+                duration=Duration(seconds=duration_seconds),
+            )
+        except EngineError:
+            raise
+        except Exception as e:
+            raise EngineError(f"Synthesis failed: {e}") from e
+
+    def dispose(self) -> None:
+        """Release session resources. Idempotent."""
+        self._disposed = True
+
+
+class KokoroEngine:
+    """Engine implementation for Kokoro.
+
+    Factory for KokoroSession instances. Stateless and thread-safe.
+    """
+
+    def __init__(self, pipeline: Any) -> None:
+        self._pipeline = pipeline
+        self._disposed = False
+
+    def createSession(self) -> KokoroSession:
+        """Create a new KokoroSession."""
+        if self._disposed:
+            raise EngineError("Engine disposed")
+        return KokoroSession(self._pipeline)
+
+    def dispose(self) -> None:
+        """Release engine resources. Idempotent."""
+        self._disposed = True
+
+    def listVoices(self, sourceId: str) -> list[VoiceManifest]:
+        """List available Kokoro voices. Implements VoiceLister capability.
+
+        Note: Static voices are declared in the plugin manifest.
+        This method is a fallback for dynamic plugins.
+        """
+        if self._disposed:
+            raise EngineError("Engine disposed")
+        return []

plugins/supertonic/__init__.py

@@ -0,0 +1,136 @@
+"""SuperTonic TTS Plugin for the TTS Plugin Architecture.
+
+This plugin provides a SuperTonic-based TTS engine that implements the
+Plugin API contract. It wraps the existing SuperTonic backend in the
+new Engine/EngineSession architecture.
+
+Exports:
+    - PLUGIN_MANIFEST: PluginManifest
+    - MODEL_REQUIREMENTS: list[ModelManifest]
+    - create_engine: Factory function
+"""
+
+from __future__ import annotations
+
+from pathlib import Path
+from typing import Any
+
+from abogen.tts_plugin.engine import Engine
+from abogen.tts_plugin.host_context import HostContext
+from abogen.tts_plugin.manifest import (
+    AudioFormatManifest,
+    EngineManifest,
+    ModelManifest,
+    ParameterManifest,
+    PluginManifest,
+    RequirementManifest,
+    VoiceManifest,
+    VoiceSourceManifest,
+)
+from abogen.tts_plugin.types import EngineConfig
+
+from .engine import SuperTonicEngine
+
+
+def _load_supertonic_pipeline() -> Any:
+    """Lazy-load SuperTonic dependencies and create pipeline."""
+    from plugins.supertonic.pipeline import SupertonicPipeline
+
+    return SupertonicPipeline(
+        sample_rate=24000,
+        auto_download=True,
+        total_steps=5,
+    )
+
+
+PLUGIN_MANIFEST = PluginManifest(
+    id="supertonic",
+    name="SuperTonic",
+    version="0.1.0",
+    api_version="1.0",
+    description="SuperTonic TTS engine - fast high-quality text-to-speech",
+    author="SuperTonic Team",
+    capabilities=("voice_list",),
+    requires=RequirementManifest(
+        internet=False,
+    ),
+    engine=EngineManifest(
+        voiceSources=(
+            VoiceSourceManifest(
+                id="builtin",
+                name="Built-in Voices",
+                type="list",
+                config={"voices": "See listVoices()"},
+            ),
+        ),
+        parameters=(
+            ParameterManifest(
+                id="speed",
+                name="Speed",
+                description="Speech speed multiplier",
+                type="float",
+                default=1.0,
+                min=0.7,
+                max=2.0,
+                step=0.1,
+            ),
+            ParameterManifest(
+                id="total_steps",
+                name="Quality Steps",
+                description="Inference steps (higher = better quality, slower)",
+                type="int",
+                default=5,
+                min=2,
+                max=15,
+                step=1,
+            ),
+        ),
+        audioFormats=(
+            AudioFormatManifest(mime="audio/wav", extension="wav"),
+        ),
+    ),
+    voices=(
+        VoiceManifest(id="M1", name="Male 1", tags=("male",)),
+        VoiceManifest(id="M2", name="Male 2", tags=("male",)),
+        VoiceManifest(id="M3", name="Male 3", tags=("male",)),
+        VoiceManifest(id="M4", name="Male 4", tags=("male",)),
+        VoiceManifest(id="M5", name="Male 5", tags=("male",)),
+        VoiceManifest(id="F1", name="Female 1", tags=("female",)),
+        VoiceManifest(id="F2", name="Female 2", tags=("female",)),
+        VoiceManifest(id="F3", name="Female 3", tags=("female",)),
+        VoiceManifest(id="F4", name="Female 4", tags=("female",)),
+        VoiceManifest(id="F5", name="Female 5", tags=("female",)),
+    ),
+)
+
+MODEL_REQUIREMENTS: list[ModelManifest] = []
+
+
+def create_engine(
+    context: HostContext,
+    model_path: Path | None,
+    config: EngineConfig,
+) -> Engine:
+    """Create a SuperTonic engine instance.
+
+    This function is the plugin entry point. It must be atomic:
+    succeed fully or raise EngineError and clean up.
+
+    Args:
+        context: Host services (config dir, logger, http client).
+        model_path: Resolved model path, or None for default.
+        config: Engine initialization settings (device, etc.).
+
+    Returns:
+        A fully initialized SuperTonicEngine instance.
+
+    Raises:
+        EngineError: On failure. Cleans up partially created resources.
+    """
+    try:
+        pipeline = _load_supertonic_pipeline()
+        engine = SuperTonicEngine(pipeline)
+        return engine
+    except Exception as e:
+        from abogen.tts_plugin.errors import EngineError as EngineErrorClass
+        raise EngineErrorClass(f"Failed to create SuperTonic engine: {e}") from e

plugins/supertonic/engine.py

@@ -0,0 +1,125 @@
+"""SuperTonic Engine adapter for the TTS Plugin Architecture.
+
+This module adapts the existing SuperTonic backend to the new Engine/EngineSession
+protocol. It wraps the SupertonicPipeline without modifying it.
+"""
+
+from __future__ import annotations
+
+import io
+import logging
+from typing import Any
+
+import numpy as np
+
+from abogen.tts_plugin.capabilities import VoiceLister
+from abogen.tts_plugin.engine import Engine, EngineSession
+from abogen.tts_plugin.errors import EngineError
+from abogen.tts_plugin.manifest import VoiceManifest
+from abogen.tts_plugin.types import (
+    AudioFormat,
+    Duration,
+    SynthesisRequest,
+    SynthesizedAudio,
+)
+
+logger = logging.getLogger(__name__)
+
+# Sample rate for SuperTonic audio
+_SUPERTONIC_SAMPLE_RATE = 24000
+
+
+class SuperTonicSession:
+    """EngineSession implementation for SuperTonic.
+
+    Owns mutable execution state for synthesis.
+    NOT thread-safe.
+    """
+
+    def __init__(self, pipeline: Any) -> None:
+        self._pipeline = pipeline
+        self._disposed = False
+
+    def synthesize(self, request: SynthesisRequest) -> SynthesizedAudio:
+        """Synthesize audio from text using SuperTonic."""
+        if self._disposed:
+            raise EngineError("Session disposed")
+
+        try:
+            import soundfile as sf
+
+            voice = request.voice.key
+            speed = float(request.parameters.values.get("speed", 1.0))
+            total_steps = request.parameters.values.get("total_steps", None)
+            split_pattern = request.parameters.values.get("split_pattern", None)
+
+            if total_steps is not None:
+                total_steps = int(total_steps)
+
+            audio_parts: list[np.ndarray] = []
+            for segment in self._pipeline(
+                request.text,
+                voice=voice,
+                speed=speed,
+                split_pattern=split_pattern,
+                total_steps=total_steps,
+            ):
+                audio_parts.append(segment.audio)
+
+            if not audio_parts:
+                return SynthesizedAudio(
+                    data=b"",
+                    format=AudioFormat(mime="audio/wav", extension="wav"),
+                    duration=Duration(seconds=0.0),
+                )
+
+            combined = np.concatenate(audio_parts).astype("float32", copy=False)
+            buf = io.BytesIO()
+            sf.write(buf, combined, self._pipeline.sample_rate, format="WAV")
+            audio_bytes = buf.getvalue()
+            duration_seconds = len(combined) / self._pipeline.sample_rate
+
+            return SynthesizedAudio(
+                data=audio_bytes,
+                format=AudioFormat(mime="audio/wav", extension="wav"),
+                duration=Duration(seconds=duration_seconds),
+            )
+        except EngineError:
+            raise
+        except Exception as e:
+            raise EngineError(f"Synthesis failed: {e}") from e
+
+    def dispose(self) -> None:
+        """Release session resources. Idempotent."""
+        self._disposed = True
+
+
+class SuperTonicEngine:
+    """Engine implementation for SuperTonic.
+
+    Factory for SuperTonicSession instances. Stateless and thread-safe.
+    """
+
+    def __init__(self, pipeline: Any) -> None:
+        self._pipeline = pipeline
+        self._disposed = False
+
+    def createSession(self) -> SuperTonicSession:
+        """Create a new SuperTonicSession."""
+        if self._disposed:
+            raise EngineError("Engine disposed")
+        return SuperTonicSession(self._pipeline)
+
+    def dispose(self) -> None:
+        """Release engine resources. Idempotent."""
+        self._disposed = True
+
+    def listVoices(self, sourceId: str) -> list[VoiceManifest]:
+        """List available SuperTonic voices. Implements VoiceLister capability.
+        
+        Note: Static voice catalog is declared in plugin manifest.
+        This method is retained for VoiceLister interface compliance.
+        """
+        if self._disposed:
+            raise EngineError("Engine disposed")
+        return []